Chapter 7 Method 3: One-Stage Individual Participant Analyses Reported Together

7.1 Comparisons Across the Taxonomy

We again need to combine data. However, rather than combining data across studies, for the two-stage approach, we’ll be combining data within studies in order to run separate analyses for each before combining via meta-analytic tools.

To do: ADD HETEROGENEITY ESTIMATES AND OTHER META-ANALYTIC TERMS

7.1.1 Tables

7.1.1.1 Meta-Analytic Estimates

loadRData <- function(fileName, type, method, obj, dir){
#loads an RData file, and returns it
    path <- sprintf("%s/results/%s/%s/%s/%s", local_path, method, type, dir, fileName)
    # print(path)
    load(path)
    get(ls()[grepl(obj, ls())])
}

nested_ipd_fx <- crossing(type = c("Frequentist", "Bayesian")
         , method = c("1a_ipd_reg", "1b_ipd_fixef", "2a_ipd_dc", "2b_ipd_mlm", "3_ipd_meta")) %>%
  mutate(dir = ifelse(method == "3_ipd_meta", "metaSummary", "summary")
         , file = pmap(list(method, type, dir, local_path), ~list.files(sprintf("%s/results/%s/%s/%s", ..4, ..1, ..2, ..3)))) %>%
  # filter(type != "Bayesian") %>%
  unnest(file) %>%
  mutate(fx = pmap(list(file, type, method, "fx", dir), loadRData)) %>%
  separate(file, c("Outcome", "Trait", "Moderator", "Covariate"), sep = "_") %>%
  mutate(Covariate = str_remove_all(Covariate, ".RData"))

# loadRData <- function(fileName, obj){
# #loads an RData file, and returns it
#     path <- sprintf("%s/%s", res_path, fileName)
#     # print(path)
#     load(url(path))
#     get(ls()[grepl(obj, ls())])
# }

# library(httr)
# repo_req <- GET("https://api.github.com/repos/emoriebeck/data-synthesis-tutorial/git/trees/main?recursive=1")
# stop_for_status(repo_req)
# repo_filelist <- unlist(lapply(content(req)$tree, "[", "path"), use.names = F)
# 
# list_files_github <- function(method, type, dir){
#   grep(sprintf("results/%s/%s/%s", method, type, dir), repo_filelist, value = TRUE, fixed = TRUE)
# }
# 
# nested_ipd_fx <- crossing(type = c("Frequentist", "Bayesian")
#          , method = c("1a_ipd_reg", "1b_ipd_fixef", "2a_ipd_dc", "2b_ipd_mlm", "3_ipd_meta")) %>%
#   mutate(dir = ifelse(method == "3_ipd_meta", "metaSummary", "summary")
#          , file = pmap(list(method, type, dir), list_files_github)) %>%
#          # , file = pmap(list(method, type, dir, local_path), ~list.files(sprintf("%s/results/%s/%s/%s", ..4, ..1, ..2, ..3)))) %>%
#   # filter(type != "Bayesian") %>%
#   unnest(file) %>%
#   filter(grepl(".RData", file)) %>%
#   mutate(fx = pmap(list(file, "fx"), loadRData)) 

# cols_ord <- paste(rep(c("b", "CI"), times = 5), rep(c("E", "A", "C", "N", "O"), each = 2), sep = "_")

ipd_fx_tab <-
  nested_ipd_fx %>%
  unnest(fx) %>%
  mutate(term = ifelse(method == "3_ipd_meta", 
                       str_replace_all(term, "metamod", paste0("p_value:", Moderator)), term)) %>%
  filter((Moderator == "none" & term == "p_value") |
         (Moderator != "none" & grepl("p_value:", term)
          & !grepl("p_value:study", term)
          & !(grepl("cor_", term) | grepl("sd_", term)))) %>%
  # filter(!Moderator %in% unique(stdyModers$short_name)) %>%
  # filter(!Moderator %in% c("scale", "continent", "country")) %>%
  mutate(sig = ifelse(sign(conf.low) == sign(conf.high), "sig", "ns"),
         mod_type = ifelse(Moderator %in% moders$short_name, "Person-Level", "Study-Level"),
         Outcome = factor(Outcome, outcomes$short_name, outcomes$long_name),
         Covariate = factor(Covariate, covars$short_name, str_wrap(covars$long_name, 15)),
         term = str_remove_all(term, "p_value:"),
         term = mapvalues(term, c("scaleBFIMS", "scaleIPIPNEO", "scaleTDAM40", "countryTheNetherlands", "gender")
                          , c("scaleBFI-S", "scaleIPIP NEO", "scaleTDA-40", "countryThe Netherlands", "genderFemale")),
         term = str_replace(term, "metamod", Moderator),
         term = factor(term, c(covars$short_term, moders$short_term, stdyModers$short_term),
                       c(covars$long_term, moders$long_term, stdyModers$long_term)),
         Moderator = factor(Moderator, c(moders$short_name, stdyModers$short_name)
                            , c(moders$long_name, stdyModers$long_name))) %>%
  mutate_at(vars(estimate, conf.low, conf.high), ~ifelse(abs(.) < .01, sprintf("%.3f", .), sprintf("%.2f", .))) %>%
  mutate(est = sprintf("%s<br>[%s, %s]", estimate, conf.low, conf.high)
         , est = ifelse(sig == "sig", sprintf("<strong>%s</strong>", est), est)) %>%
  # mutate_at(vars(estimate, CI), ~ifelse(sig == "sig", sprintf("\\textbf{%s}", .), .)) %>%
  select(type, method, Outcome, Trait, Moderator, mod_type, Covariate, term, est) %>%
  pivot_wider(names_from = "Trait", values_from = est) %>%
  select(type:term, E, A, C, N, O) 

## table function 
ipd_fx_tab_fun <- function(d, type, moder_type, cov){
  md <- mapvalues(moder_type, c("Study-Level", "Person-Level"), c("study", "person")
                  , warn_missing = F)
  cv <- mapvalues(cov, covars$long_name, covars$short_name, warn_missing = F)
  d <- d %>% arrange(method, Moderator)
  rs <- d %>% mutate(method = factor(method, mthds$old_name, mthds$long_name)) %>%
    group_by(method) %>% tally() %>% 
    mutate(end = cumsum(n), start = lag(end) + 1, start = ifelse(is.na(start), 1, start))
  if(all((d %>% group_by(Moderator, method) %>% tally())$n == 1)){
    cs <-  rep(1,6)
    cln <- c(" ", rep("<em>b</em> [CI]", times = 5)) 
    al <- c("r", rep("c", 5)) 
    d <- d %>% select(-Moderator)
  } else {
    cs <- c(2, rep(1,5))
    cln <-  c(" ", "Term", rep("<em>b</em> [CI]", times = 5))
    al <- c("r", "r", rep("c", 5))
  }
  names(cs) <- c(" ", traits$short_name)
  # caption 
  cap <- if(md == "person") "Cross-Method Comparison of Overall Effects and Person-Level Moderators of Personality-Crystallized Domain Associations" else "Cross-Method Comparison of Overall Study-Level Moderators of Personality-Crystallized Domain Associations"
  tab <- d %>%
    select(-method) %>%
    kable(., "html"
    # kable(., "latex"
          , escape = F
          , col.names = cln
          , align = al
          , caption = cap
    ) %>% 
    kable_classic(full_width = F, html_font = "Times New Roman") %>%
    add_header_above(cs) %>%
    collapse_rows(1, valign = "top", row_group_label_position = "stack")
  for (i in 1:nrow(rs)) {
    tab <- tab %>% kableExtra::group_rows(rs$method[i], rs$start[i], rs$end[i])
  }
  save_kable(tab, file = sprintf("%s/results/tables/cross-method/overall/%s_%s_%s.html"
                                 , local_path, type, md, cv))
  return(tab)
}

nested_ipd_fx_tab <- ipd_fx_tab %>%
  filter(Covariate %in% c("Fully Adjusted", "Unadjusted")) %>%
  group_by(type, mod_type, Outcome, Covariate) %>%
  nest() %>%
  ungroup() %>%
  mutate(tab = pmap(list(data, type, mod_type, Covariate), ipd_fx_tab_fun))

# save(nested_ipd_fx_tab, file = sprintf("%s/manuscript/results/ct_fx_tab.RData", res_path))

nested_ipd_fx_tab$tab[[6]]

Table 7.1: Cross-Method Comparison of Overall Effects and Person-Level Moderators of Personality-Crystallized Domain Associations

	E	A	C	N	O
	b [CI]	b [CI]	b [CI]	b [CI]	b [CI]
1A: Pooled Analysis of Individual Participant Data
Personality	-0.08 [-0.10, -0.07]	-0.14 [-0.16, -0.12]	0.007 [-0.01, 0.02]	-0.003 [-0.02, 0.01]	0.20 [0.19, 0.22]
Age	0.000 [-0.001, 0.002]	-0.001 [-0.002, 0.001]	-0.002 [-0.003, -0.000]	0.002 [0.001, 0.003]	-0.001 [-0.002, 0.000]
Gender (Male v Female)	0.07 [0.04, 0.11]	0.04 [0.008, 0.08]	0.007 [-0.03, 0.04]	-0.03 [-0.05, 0.002]	-0.01 [-0.05, 0.02]
Education (Years)	0.005 [0.000, 0.009]	-0.004 [-0.008, 0.001]	-0.007 [-0.01, -0.002]	-0.002 [-0.005, 0.002]	0.002 [-0.003, 0.007]
1B: Pooled Analysis of Individual Participant Data with Cluster Corrected Errors
Personality	-0.08 [-0.27, 0.10]	-0.14 [-0.36, 0.08]	0.007 [-0.17, 0.18]	-0.003 [-0.15, 0.14]	0.20 [0.06, 0.34]
Age	0.000 [-0.004, 0.005]	-0.001 [-0.005, 0.003]	-0.002 [-0.006, 0.003]	0.002 [0.000, 0.004]	-0.001 [-0.006, 0.004]
Gender (Male v Female)	0.07 [0.004, 0.14]	0.04 [-0.04, 0.12]	0.007 [-0.11, 0.12]	-0.03 [-0.14, 0.08]	-0.01 [-0.08, 0.05]
Education (Years)	0.005 [-0.008, 0.02]	-0.004 [-0.03, 0.02]	-0.007 [-0.03, 0.02]	-0.002 [-0.02, 0.01]	0.002 [-0.008, 0.01]
2A: Pooled Analysis of Individual Participant Data using Contrasts
Personality	0.05 [0.02, 0.08]	-0.001 [-0.03, 0.03]	0.04 [0.02, 0.07]	-0.13 [-0.15, -0.11]	0.29 [0.25, 0.32]
Age	-0.003 [-0.008, 0.003]	-0.003 [-0.006, 0.001]	-0.005 [-0.008, -0.001]	0.005 [0.001, 0.009]	0.002 [-0.003, 0.007]
Gender (Male v Female)	0.06 [0.003, 0.12]	0.02 [-0.04, 0.08]	-0.02 [-0.08, 0.03]	-0.03 [-0.08, 0.02]	0.005 [-0.07, 0.08]
Education (Years)	-0.002 [-0.01, 0.009]	-0.003 [-0.02, 0.010]	0.010 [-0.001, 0.02]	-0.003 [-0.01, 0.006]	-0.003 [-0.02, 0.01]
2B: Pooled Analysis of Individual Participant Data using Random Effects
Personality	0.04 [0.009, 0.08]	0.005 [-0.08, 0.09]	0.05 [-0.03, 0.12]	-0.12 [-0.15, -0.09]	0.27 [0.18, 0.36]
Age	-0.006 [-0.01, 0.000]	-0.002 [-0.006, 0.003]	-0.003 [-0.008, 0.002]	0.005 [-0.04, 0.05]	0.002 [-0.10, 0.10]
Gender (Male v Female)	0.05 [-0.02, 0.12]	-0.000 [-0.07, 0.07]	0.003 [-0.04, 0.05]	-0.01 [-0.05, 0.02]	0.005 [-0.07, 0.08]
Education (Years)	-0.003 [-0.01, 0.005]	-0.002 [-0.02, 0.01]	0.01 [-0.009, 0.03]	0.002 [-0.006, 0.010]	-0.01 [-0.09, 0.06]
3: Separate Analyses Followed by Meta-Analysis
Personality	0.04 [0.009, 0.08]	0.003 [-0.08, 0.09]	0.04 [-0.04, 0.12]	-0.12 [-0.15, -0.09]	0.27 [0.18, 0.37]
Age	-0.000 [-0.003, 0.002]	-0.001 [-0.002, 0.000]	-0.002 [-0.007, 0.003]	0.001 [-0.003, 0.005]	0.001 [-0.005, 0.008]
Gender (Male v Female)	0.06 [0.002, 0.11]	0.03 [-0.01, 0.06]	-0.008 [-0.05, 0.03]	-0.006 [-0.04, 0.03]	-0.03 [-0.07, 0.02]
Education (Years)	-0.003 [-0.01, 0.010]	-0.006 [-0.02, 0.010]	0.004 [-0.01, 0.02]	-0.002 [-0.01, 0.008]	-0.005 [-0.02, 0.008]

ipd_fx_tab_stdm <-ipd_fx_tab %>% 
  filter(type == "Frequentist" & mod_type == "Study-Level" & Covariate %in% "Fully Adjusted" & 
           !method %in% c("2a_ipd_dc", "1b_ipd_fixef")) %>%
  pivot_longer(names_to = "Trait"
               , values_to = "value"
               , cols = E:O) %>%
  pivot_wider(names_from = c("method", "Trait")
              , values_from = "value") 

rs <- ipd_fx_tab_stdm %>% 
  arrange(type, Outcome, Moderator, term) %>%
  group_by(Moderator) %>% tally() %>% 
  mutate(end = cumsum(n), start = lag(end) + 1, start = ifelse(is.na(start), 1, start))

cln1 <- rep(1,16); names(cln1) <- c(" ", rep(c("E", "A", "C", "N", "O"), times = 3))
cln2 <- c(1, rep(5, 3)); names(cln2) <- c(" ", "Method 1A", "Method 2B", "Method 3")

cap <- "<strong>Table X</strong><br><em>Cross-Method Comparison of Overall Study-Level Moderators of Personality-Crystallized Domain Associations</em>"

tab <- ipd_fx_tab_stdm %>%
  arrange(type, Outcome, Moderator, term) %>%
  mutate(term = mapvalues(term, stdyModers$long_term, stdyModers$medium_term)) %>%
  mutate_at(vars(`1a_ipd_reg_E`:`3_ipd_meta_O`), ~str_replace_all(., "0\\.", ".")) %>%
  # mutate_at(vars(`1a_ipd_reg_E`:`3_ipd_meta_O`), ~str_replace_all(., "-0.", "-.")) %>%
  select(-type, -Outcome, -Moderator, -mod_type, -Covariate) %>%
  kable(., "html"
        , col.names = c("Term", rep("b [CI]", 15))
        , align = c("r", rep("c", 15))
        , escape = F
        , caption = cap
        ) %>%
  kable_classic(full_width = F, html_font = "Times New Roman") %>%
  add_header_above(cln1) %>%
  add_header_above(cln2)

for(i in 1:nrow(rs)){
  tab <- tab %>%
    kableExtra::group_rows(rs$Moderator[i], rs$start[i], rs$end[i])
}
save_kable(tab, file = sprintf("%s/results/tables/cross-method/overall/Frequentist_crystallized_study_all.html", local_path))
tab

Table 7.2: Table X
Cross-Method Comparison of Overall Study-Level Moderators of Personality-Crystallized Domain Associations

	Method 1A					Method 2B					Method 3
	E	A	C	N	O	E	A	C	N	O	E	A	C	N	O
Term	b [CI]	b [CI]	b [CI]	b [CI]	b [CI]	b [CI]	b [CI]	b [CI]	b [CI]	b [CI]	b [CI]	b [CI]	b [CI]	b [CI]	b [CI]
Continent
North America v Europe	.15 [.10, .20]	-.03 [-.09, .04]	-.04 [-.10, .01]	.06 [.03, .09]	.04 [-.01, .10]	.07 [.004, .14]	-.12 [-.26, .03]	-.12 [-.24, .005]	-.03 [-.06, .009]	.14 [-.08, .36]	.06 [-.02, .14]	-.08 [-.19, .03]	-.11 [-.21, -.006]	.02 [-.04, .08]	.08 [-.13, .28]
North America v Australia	.06 [.02, .09]	.002 [-.04, .04]	-.04 [-.08, -.008]	-.13 [-.17, -.10]	.11 [.08, .14]	.03 [-.05, .10]	-.01 [-.18, .15]	-.02 [-.16, .11]	-.11 [-.14, -.08]	.11 [-.19, .40]	.03 [-.06, .12]	-.03 [-.15, .08]	-.06 [-.17, .06]	-.05 [-.13, .04]	.06 [-.21, .33]
Country
US v Germany	.20 [.12, .27]	.005 [-.08, .09]	-.06 [-.15, .04]	.10 [.03, .17]	.02 [-.04, .09]	.08 [-.02, .18]	-.009 [-.10, .08]	-.05 [-.19, .09]	-.02 [-.09, .05]	.12 [-.15, .38]	.09 [.002, .18]	-.03 [-.12, .07]	-.06 [-.12, -.003]	.02 [-.08, .12]	.04 [-.20, .28]
US v Sweden	.08 [.02, .15]	-.22 [-.33, -.11]	-.21 [-.30, -.11]	.03 [-.03, .09]	.23 [.09, .36]	.07 [-.03, .16]	-.23 [-.35, -.12]	-.20 [-.34, -.06]	-.05 [-.11, .01]	.22 [-.13, .58]	.03 [-.06, .13]	-.15 [-.28, -.02]	-.18 [-.27, -.09]	.03 [-.07, .13]	.15 [-.16, .46]
US v Netherlands				-.02 [-.07, .03]					-.02 [-.06, .03]					.03 [-.08, .14]
US v Australia	.06 [.02, .09]	.001 [-.04, .04]	-.05 [-.08, -.01]	-.13 [-.17, -.10]	.11 [.08, .14]	.02 [-.06, .11]	-.008 [-.05, .03]	-.02 [-.13, .08]	-.11 [-.14, -.08]	.11 [-.21, .43]	.03 [-.05, .12]	-.03 [-.11, .06]	-.06 [-.10, -.03]	-.04 [-.14, .06]	.06 [-.22, .34]
Personality Scale
NEO-FFI v DPQ				.11 [.06, .17]					.009 [-.09, .11]					.07 [.01, .12]
NEO-FFI v Eysenck	.02 [-.15, .20]	-.23 [-.36, -.09]	-.15 [-.28, -.02]	.21 [.14, .27]	-.06 [-.25, .13]	.09 [-.007, .18]	-.24 [-9.45, 8.97]	-.21 [-.33, -.10]	-.02 [-.11, .08]	.14 [-.50, .77]	.02 [-.07, .12]		-.21 [-.31, -.11]	.07 [-.005, .15]	.07 [-.37, .51]
NEO-FFI v MIDI	-.06 [-.22, .11]	-.005 [-.09, .08]	.06 [-.04, .15]	.14 [.10, .18]	-.28 [-.42, -.14]	-.002 [-.08, .08]	-.007 [-9.22, 9.20]	.01 [-.06, .08]	.03 [-.06, .12]	-.07 [-.70, .55]	-.04 [-.11, .03]		-.02 [-.08, .04]	.09 [.04, .14]	-.13 [-.55, .29]
NEO-FFI v BFI-S	.07 [-.11, .25]			.14 [.05, .22]	-.32 [-.47, -.16]	.12 [.005, .23]	-.01 [-9.22, 9.20]	-.07 [-.18, .05]	.03 [-.09, .14]	-.12 [-.75, .51]	.10 [.01, .18]		-.09 [-.17, -.010]	.08 [.02, .14]	-.14 [-.57, .28]
NEO-FFI v IPIP NEO				.10 [.01, .19]		.11 [-.009, .22]	.01 [-9.20, 9.22]	-.12 [-.22, -.01]	-.003 [-.12, .12]	.01 [-.61, .64]	.08 [-.04, .20]		-.13 [-.24, -.01]	.06 [-.04, .17]	.04 [-.39, .48]
TDA-40	-.003 [-.17, .16]	-.004 [-.09, .08]	.01 [-.08, .10]	.02 [-.02, .07]	-.17 [-.31, -.03]	.04 [-.04, .13]	-.010 [-9.22, 9.20]	-.04 [-.11, .02]	-.08 [-.17, .009]	.02 [-.60, .65]	.03 [-.05, .10]		-.09 [-.15, -.03]	-.003 [-.05, .05]	-.01 [-.43, .41]
Baseline Age
Study Baseline Age	-.004 [-.005, -.003]	-.001 [-.002, .001]	-.000 [-.002, .001]	-.000 [-.001, .001]	-.004 [-.005, -.003]	-.001 [-.003, .002]	.002 [-.003, .007]	.002 [-.002, .006]	.001 [-.001, .003]	-.000 [-.007, .007]	-.001 [-.003, .002]	.002 [-.001, .004]	.002 [-.001, .006]	-.000 [-.003, .002]	.001 [-.005, .007]
Baseline Year
Study Baseline Year	-.003 [-.006, .001]	.007 [.002, .01]	.007 [.003, .01]	.002 [.000, .005]	-.010 [-.01, -.004]	-.000 [-.005, .005]	.008 [.004, .01]	.005 [-.002, .01]	.001 [-.003, .005]	-.008 [-.02, .002]	.001 [-.004, .006]	.005 [.001, .009]	.004 [-.003, .01]	-.000 [-.005, .004]	-.006 [-.01, .003]
Prediction Interval
Prediction Interval	.002 [-.005, .009]	-.03 [-.04, -.03]	-.03 [-.03, -.02]	-.006 [-.01, -.000]	.02 [.01, .03]	-.003 [-.01, .009]	-.01 [-.02, -.004]	-.009 [-.02, .005]	-.001 [-.01, .010]	.009 [-.02, .04]	-.003 [-.01, .009]	-.007 [-.02, .001]	-.008 [-.02, .006]	.001 [-.010, .01]	.007 [-.01, .03]

7.1.1.2 Sample-Specific Estimates

loadRData <- function(fileName, type, method, obj, dir){
#loads an RData file, and returns it
    print(paste(type, method, fileName, dir, obj))
    path <- sprintf("%s/results/%s/%s/%s/%s", local_path, method, type, dir, fileName)
    load(path)
    get(ls()[grepl(obj, ls())])
}

nested_ipd_rx <- 
  crossing(type = c("Frequentist", "Bayesian")
         , method = c("2a_ipd_dc", "2b_ipd_mlm", "3_ipd_meta")) %>%
  mutate(dir = ifelse(method == "3_ipd_meta", "studySummary", "summary")
         , obj = "rx" # ifelse(method == "3_ipd_meta" & type == "Frequentist", "fx", "rx")
           , file = pmap(list(method, type, dir, local_path), ~list.files(sprintf("%s/results/%s/%s/%s", ..4, ..1, ..2, ..3)))) %>%
    # filter(type != "Bayesian") %>%
    unnest(file) %>%
    # filter(method == "3_ipd_meta" & type == "Frequentist") %>%
    separate(file, c("Outcome", "Trait", "Moderator", "Covariate", "study"), sep = "_", remove = F) %>%
    filter(!Moderator %in% stdyModers$short_name) %>%
    mutate(rx = pmap(list(file, type, method, obj, dir), loadRData)) %>%
    mutate(study = str_remove_all(study, ".RData")
           , Covariate = str_remove_all(Covariate, ".RData")) %>%
  filter(!Moderator %in% stdyModers$short_name) %>%
  mutate(rx = ifelse(!is.na(study), map2(rx, study, ~(.x) %>% mutate(study = .y)), rx)) %>%
  select(-study,  -dir, -file) 

## [1] "Bayesian 2a_ipd_dc crystallized_A_age_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_A_age_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_A_education_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_A_education_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_A_gender_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_A_gender_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_A_none_age.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_A_none_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_A_none_education.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_A_none_gender.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_A_none_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_C_age_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_C_age_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_C_education_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_C_education_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_C_gender_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_C_gender_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_C_none_age.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_C_none_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_C_none_education.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_C_none_gender.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_C_none_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_E_age_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_E_age_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_E_education_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_E_education_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_E_gender_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_E_gender_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_E_none_age.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_E_none_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_E_none_education.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_E_none_gender.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_E_none_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_N_age_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_N_age_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_N_education_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_N_education_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_N_gender_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_N_gender_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_N_none_age.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_N_none_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_N_none_education.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_N_none_gender.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_N_none_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_O_age_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_O_age_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_O_education_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_O_education_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_O_gender_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_O_gender_none.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_O_none_age.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_O_none_all.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_O_none_education.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_O_none_gender.RData summary rx"
## [1] "Bayesian 2a_ipd_dc crystallized_O_none_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_A_age_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_A_age_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_A_education_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_A_education_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_A_gender_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_A_gender_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_A_none_age.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_A_none_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_A_none_education.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_A_none_gender.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_A_none_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_C_age_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_C_age_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_C_education_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_C_education_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_C_gender_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_C_gender_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_C_none_age.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_C_none_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_C_none_education.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_C_none_gender.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_C_none_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_E_age_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_E_age_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_E_education_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_E_education_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_E_gender_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_E_gender_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_E_none_age.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_E_none_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_E_none_education.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_E_none_gender.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_E_none_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_N_age_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_N_age_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_N_education_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_N_education_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_N_gender_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_N_gender_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_N_none_age.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_N_none_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_N_none_education.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_N_none_gender.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_N_none_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_O_age_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_O_age_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_O_education_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_O_education_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_O_gender_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_O_gender_none.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_O_none_age.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_O_none_all.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_O_none_education.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_O_none_gender.RData summary rx"
## [1] "Bayesian 2b_ipd_mlm crystallized_O_none_none.RData summary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_age_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_age_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_age_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_age_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_age_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_age_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_age_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_age_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_age_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_age_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_age_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_age_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_education_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_education_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_education_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_education_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_education_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_education_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_education_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_education_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_education_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_education_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_education_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_education_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_gender_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_gender_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_gender_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_gender_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_gender_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_gender_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_gender_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_gender_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_gender_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_gender_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_gender_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_gender_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_age_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_age_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_age_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_age_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_age_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_age_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_education_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_education_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_education_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_education_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_education_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_education_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_gender_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_gender_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_gender_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_gender_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_gender_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_gender_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_A_none_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_all_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_none_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_age_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_all_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_none_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_education_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_all_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_none_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_gender_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_age_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_age_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_age_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_age_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_age_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_age_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_age_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_all_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_education_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_education_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_education_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_education_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_education_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_education_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_education_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_gender_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_gender_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_gender_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_gender_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_gender_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_gender_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_gender_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_none_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_C_none_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_all_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_all_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_all_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_none_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_none_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_none_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_age_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_all_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_all_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_all_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_none_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_none_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_none_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_education_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_all_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_all_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_all_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_none_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_none_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_none_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_gender_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_age_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_age_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_age_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_age_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_age_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_age_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_age_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_age_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_age_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_all_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_all_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_all_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_education_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_education_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_education_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_education_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_education_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_education_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_education_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_education_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_education_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_gender_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_gender_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_gender_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_gender_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_gender_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_gender_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_gender_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_gender_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_gender_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_none_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_none_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_none_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_E_none_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_all_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_all_LASA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_all_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_all_MARS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_all_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_none_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_none_LASA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_none_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_none_MARS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_none_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_age_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_all_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_all_LASA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_all_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_all_MARS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_all_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_none_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_none_LASA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_none_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_none_MARS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_none_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_education_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_all_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_all_LASA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_all_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_all_MARS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_all_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_none_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_none_LASA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_none_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_none_MARS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_none_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_gender_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_age_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_age_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_age_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_age_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_age_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_age_LASA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_age_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_age_MARS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_age_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_age_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_age_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_all_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_all_LASA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_all_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_all_MARS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_all_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_education_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_education_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_education_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_education_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_education_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_education_LASA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_education_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_education_MARS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_education_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_education_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_education_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_gender_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_gender_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_gender_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_gender_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_gender_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_gender_LASA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_gender_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_gender_MARS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_gender_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_gender_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_gender_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_none_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_none_LASA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_none_MAP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_none_MARS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_none_OCTO-TWIN.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_N_none_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_all_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_none_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_age_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_all_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_none_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_education_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_all_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_none_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_gender_none_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_age_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_age_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_age_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_age_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_age_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_age_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_age_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_all_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_all_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_all_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_all_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_all_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_all_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_all_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_education_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_education_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_education_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_education_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_education_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_education_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_education_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_gender_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_gender_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_gender_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_gender_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_gender_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_gender_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_gender_SATSA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_none_BASE-I.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_none_EAS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_none_GSOEP.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_none_HILDA.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_none_HRS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_none_ROS.RData studySummary rx"
## [1] "Bayesian 3_ipd_meta crystallized_O_none_none_SATSA.RData studySummary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_A_age_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_A_age_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_A_education_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_A_education_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_A_gender_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_A_gender_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_A_none_age.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_A_none_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_A_none_education.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_A_none_gender.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_A_none_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_C_age_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_C_age_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_C_education_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_C_education_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_C_gender_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_C_gender_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_C_none_age.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_C_none_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_C_none_education.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_C_none_gender.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_C_none_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_E_age_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_E_age_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_E_education_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_E_education_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_E_gender_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_E_gender_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_E_none_age.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_E_none_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_E_none_education.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_E_none_gender.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_E_none_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_N_age_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_N_age_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_N_education_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_N_education_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_N_gender_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_N_gender_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_N_none_age.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_N_none_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_N_none_education.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_N_none_gender.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_N_none_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_O_age_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_O_age_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_O_education_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_O_education_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_O_gender_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_O_gender_none.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_O_none_age.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_O_none_all.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_O_none_education.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_O_none_gender.RData summary rx"
## [1] "Frequentist 2a_ipd_dc crystallized_O_none_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_A_age_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_A_age_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_A_education_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_A_education_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_A_gender_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_A_gender_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_A_none_age.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_A_none_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_A_none_education.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_A_none_gender.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_A_none_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_C_age_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_C_age_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_C_education_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_C_education_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_C_gender_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_C_gender_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_C_none_age.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_C_none_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_C_none_education.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_C_none_gender.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_C_none_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_E_age_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_E_age_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_E_education_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_E_education_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_E_gender_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_E_gender_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_E_none_age.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_E_none_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_E_none_education.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_E_none_gender.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_E_none_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_N_age_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_N_age_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_N_education_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_N_education_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_N_gender_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_N_gender_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_N_none_age.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_N_none_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_N_none_education.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_N_none_gender.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_N_none_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_O_age_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_O_age_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_O_education_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_O_education_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_O_gender_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_O_gender_none.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_O_none_age.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_O_none_all.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_O_none_education.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_O_none_gender.RData summary rx"
## [1] "Frequentist 2b_ipd_mlm crystallized_O_none_none.RData summary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_age_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_age_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_age_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_age_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_age_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_age_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_age_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_age_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_age_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_age_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_age_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_age_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_education_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_education_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_education_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_education_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_education_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_education_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_education_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_education_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_education_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_education_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_education_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_education_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_gender_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_gender_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_gender_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_gender_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_gender_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_gender_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_gender_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_gender_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_gender_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_gender_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_gender_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_gender_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_age_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_age_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_age_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_age_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_age_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_age_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_education_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_education_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_education_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_education_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_education_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_education_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_gender_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_gender_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_gender_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_gender_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_gender_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_gender_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_A_none_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_all_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_none_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_age_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_all_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_none_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_education_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_all_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_none_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_gender_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_age_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_age_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_age_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_age_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_age_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_age_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_age_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_all_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_education_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_education_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_education_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_education_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_education_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_education_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_education_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_gender_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_gender_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_gender_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_gender_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_gender_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_gender_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_gender_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_none_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_C_none_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_all_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_all_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_all_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_none_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_none_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_none_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_age_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_all_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_all_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_all_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_none_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_none_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_none_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_education_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_all_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_all_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_all_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_none_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_none_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_none_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_gender_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_age_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_age_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_age_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_age_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_age_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_age_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_age_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_age_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_age_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_all_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_all_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_all_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_education_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_education_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_education_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_education_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_education_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_education_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_education_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_education_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_education_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_gender_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_gender_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_gender_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_gender_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_gender_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_gender_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_gender_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_gender_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_gender_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_none_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_none_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_none_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_E_none_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_all_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_all_LASA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_all_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_all_MARS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_all_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_none_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_none_LASA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_none_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_none_MARS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_none_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_age_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_all_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_all_LASA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_all_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_all_MARS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_all_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_none_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_none_LASA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_none_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_none_MARS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_none_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_education_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_all_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_all_LASA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_all_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_all_MARS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_all_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_none_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_none_LASA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_none_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_none_MARS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_none_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_gender_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_age_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_age_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_age_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_age_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_age_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_age_LASA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_age_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_age_MARS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_age_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_age_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_age_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_all_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_all_LASA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_all_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_all_MARS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_all_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_education_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_education_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_education_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_education_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_education_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_education_LASA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_education_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_education_MARS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_education_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_education_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_education_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_gender_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_gender_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_gender_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_gender_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_gender_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_gender_LASA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_gender_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_gender_MARS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_gender_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_gender_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_gender_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_none_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_none_LASA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_none_MAP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_none_MARS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_none_OCTO-TWIN.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_N_none_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_all_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_none_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_age_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_all_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_none_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_education_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_all_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_none_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_gender_none_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_age_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_age_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_age_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_age_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_age_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_age_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_age_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_all_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_all_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_all_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_all_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_all_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_all_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_all_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_education_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_education_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_education_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_education_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_education_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_education_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_education_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_gender_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_gender_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_gender_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_gender_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_gender_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_gender_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_gender_SATSA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_none_BASE-I.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_none_EAS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_none_GSOEP.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_none_HILDA.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_none_HRS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_none_ROS.RData studySummary rx"
## [1] "Frequentist 3_ipd_meta crystallized_O_none_none_SATSA.RData studySummary rx"

cols_ord <- paste(rep(c("b", "CI"), times = 5), rep(c("E", "A", "C", "N", "O"), each = 2), sep = "_")

ipd_rx_tab <- 
  nested_ipd_rx %>%
  unnest(rx) %>%
  mutate(term = ifelse(is.na(term), names, term)) %>%
  filter((Moderator == "none" & term == "p_value") |
         (Moderator != "none" & grepl("p_value:", term))) %>%
  mutate(sig = ifelse(sign(conf.low) == sign(conf.high), "sig", "ns"),
         Outcome = factor(Outcome, outcomes$short_name, outcomes$long_name),
         Covariate = factor(Covariate, covars$short_name, str_wrap(covars$long_name, 15)),
         term = str_remove_all(term, "p_value:"),
         term = factor(term, c(covars$short_term, moders$short_term, stdyModers$short_term),
                       c(covars$long_term, moders$long_term, stdyModers$long_term)),
         Moderator = factor(Moderator, c(moders$short_name, stdyModers$short_name)
                            , c(moders$long_name, stdyModers$long_name))) %>%
  mutate_at(vars(estimate, conf.low, conf.high), ~ifelse(abs(.) < .01, sprintf("%.3f", .), sprintf("%.2f", .))) %>%
  mutate(CI = sprintf("[%s, %s]", conf.low, conf.high)) %>%
  mutate_at(vars(estimate, CI), ~ifelse(sig == "sig", sprintf("<strong>%s</strong>", .), .)) %>%
  select(type, method, Outcome, Trait, Moderator, Covariate, study, term, b = estimate, CI) %>%
  pivot_wider(names_from = "Trait", values_from = c("b", "CI")) %>%
  select(type:term, study, one_of(cols_ord)) 

ipd_rx_tab_fun <- function(d, type, moder){
  print(moder)
  md <- mapvalues(moder, moders$long_name, moders$short_name, warn_missing = F)
  d <- d %>% arrange(Covariate, study, method)
  rs <- d %>% group_by(Covariate) %>% tally() %>% 
    mutate(end = cumsum(n), start = lag(end) + 1, start = ifelse(is.na(start), 1, start))
  cs <- if(length(unique(d$term)) == 1) rep(2,6) else c(3, rep(2,5))
  names(cs) <- c(" ", traits$short_name)
  cln <- if(length(unique(d$term)) == 1) c(" ", "Study", rep(c("<em>b</em>", "CI"), times = 5)) else c(" ", "Study", "Term", rep(c("<em>b</em>", "[CI]"), times = 5))
  al <- if(length(unique(d$term))) c("r", "r", rep("c", 10)) else c("r", "r", "r", rep("c", 10))
  if(length(unique(d$term)) == 1) {
    d <- d %>% select(-term); dubs <- F
  } #else {
  #   rs2 <- d %>% group_by(Covariate, method) %>% tally() %>% 
  #   mutate(end = cumsum(n), start = lag(end) + 1, start = ifelse(is.na(start), 1, start))
  #   d <- d %>% select(-method); dubs <- T
  # }
  # caption 
  cap <- if(md == "none") "Cross-Method Comparison of Study-Specific Effects of Personality-Crystallized Domain Associations" else sprintf("Cross-Method Comparison of Study-Specific %s Moderation of Personality-Crystallized Domain Associations", md)
  tab <- d %>%
    select(-Covariate) %>%
    kable(., "html"
          , escape = F
          , booktabs = T
          , col.names = cln
          , align = al
          , caption = cap
    ) %>% 
    kable_classic(full_width = F, html_font = "Times New Roman") %>%
    add_header_above(cs) %>%
    collapse_rows(1, valign = "top", row_group_label_position = "stack")
  for (i in 1:nrow(rs)) {
    tab <- tab %>% kableExtra::group_rows(rs$Covariate[i], rs$start[i], rs$end[i])
  }
  # if(dubs == T) for(i in 1:nrow(rs2)) {
  #   tab <- tab %>% kableExtra::group_rows(rs2$method[i], rs2$start[i], rs2$end[i]
  #                                         , indent = T, hline_after = F)
  # }
  save_kable(tab, file = sprintf("%s/results/tables/cross-method/study-specific/%s_%s.html"
                                 , local_path, type, md))
  return(tab)
}

nested_ipd_rx_tab <- ipd_rx_tab %>%
  mutate(study = mapvalues(study, c("BASEI", "OCTOTWIN"), c("BASE", "OCTO-Twin")),
         study = mapvalues(study, c("BASE-I", "OCTO-TWIN"), c("BASE", "OCTO-Twin"))) %>%
  select(type, Moderator, Outcome, Covariate, study, method, term, everything()) %>%
  group_by(type, Moderator, Outcome) %>%
  nest() %>%
  ungroup() %>%
  mutate(tab = pmap(list(data, type, Moderator), ipd_rx_tab_fun))

## [1] Age
## 12 Levels: None Age Gender Self-Rated Physical Health Education Fully Adjusted Continent Country ... Prediction Interval
## [1] Education
## 12 Levels: None Age Gender Self-Rated Physical Health Education Fully Adjusted Continent Country ... Prediction Interval
## [1] Gender
## 12 Levels: None Age Gender Self-Rated Physical Health Education Fully Adjusted Continent Country ... Prediction Interval
## [1] None
## 12 Levels: None Age Gender Self-Rated Physical Health Education Fully Adjusted Continent Country ... Prediction Interval
## [1] Age
## 12 Levels: None Age Gender Self-Rated Physical Health Education Fully Adjusted Continent Country ... Prediction Interval
## [1] Education
## 12 Levels: None Age Gender Self-Rated Physical Health Education Fully Adjusted Continent Country ... Prediction Interval
## [1] Gender
## 12 Levels: None Age Gender Self-Rated Physical Health Education Fully Adjusted Continent Country ... Prediction Interval
## [1] None
## 12 Levels: None Age Gender Self-Rated Physical Health Education Fully Adjusted Continent Country ... Prediction Interval

tmp <- nested_ipd_rx_tab %>% filter(type == "Frequentist")
for(i in 1:4){
  cat("#####", as.character(tmp$Moderator[[i]]), "\n\n")
  print(tmp$tab[[i]])
}

7.1.1.2.1 Age

7.1.1.2.2 Education

7.1.1.2.3 Gender

7.1.1.2.4 None

7.1.1.3 Heterogeneity

loadRData <- function(fileName, type, method, obj, dir){
#loads an RData file, and returns it
    path <- sprintf("%s/results/%s/%s/%s/%s", local_path, method, type, dir, fileName)
    # print(path)
    load(path)
    get(ls()[grepl(obj, ls())])
}

nested_ipd_fx <- crossing(type = c("Frequentist", "Bayesian")
         , method = c("2b_ipd_mlm", "3_ipd_meta")) %>%
  mutate(dir = ifelse(method == "3_ipd_meta", "metaHetero", "heterogeneity")
         , file = pmap(list(method, type, dir, local_path), ~list.files(sprintf("%s/results/%s/%s/%s", ..4, ..1, ..2, ..3)))) %>%
  # filter(type != "Bayesian") %>%
  unnest(file) %>%
  mutate(fx = pmap(list(file, type, method, "fx", dir), loadRData)) %>%
  separate(file, c("Outcome", "Trait", "Moderator", "Covariate"), sep = "_") %>%
  mutate(Covariate = str_remove_all(Covariate, ".RData"))

7.1.2 Figures

7.1.2.1 Meta-Analytic Estimates

fx_forest_fun <- function(df, outcome, mod, type, cov, mthd){
  print(paste(outcome, mod))
  meth <- mapvalues(mthd, mthds$old_name, mthds$long_name, warn_missing = F)
  m <- mapvalues(mod, moders$long_name, moders$short_name, warn_missing = F)
  d <- round(max(abs(min(df$estimate)), abs(max(df$estimate))), 3)
  # stds <- unique(df$study)
  lim <- c(0-d-(d/2.5), 0+d+(d/2.5))
  brk <- if(d > .01) round(c(0-d-(d/5), 0, 0+d+(d/5)),2) else round(c(0-d-(d/5), 0, 0+d+(d/5)),3) 
  lim_high <- lim[2]*4
  lab <- str_replace(brk, "^0.", ".")#str_remove(round(c(0-d-(d/5), 0, 0+d+(d/5)),2), "^0")
  shapes <- c(15, 16, 17, 18)[1:length(unique(df$term))]
  lt <- rep("solid", length(unique(df$term)))
  titl <- if(mod == "none"){"Main Effects"} else {sprintf("Personality x %s", mod)}
  leg <- if(length(unique(df$term)) > 1){"bottom"} else {"none"}
  trm <- if(mod != "None") paste("Personality x", unique(df$term[!is.na(df$term)]))
  df <- df %>% full_join(tibble(Trait = " ", estimate = NA, n = NA))
  # df <- df %>% arrange(estimate)
  trts <- df$Trait[!df$Trait %in% c(" ")]
  df <- df %>%
    mutate_at(vars(estimate, conf.low, conf.high),
      lst(f = ~ifelse(abs(.) < .001, sprintf("%.4f", .), ifelse(abs(.) < .01, sprintf("%.3f", .), sprintf("%.2f", .))))) %>%
    mutate(Trait = factor(Trait, rev(c(" ", traits$short_name)), rev(c(" ", traits$long_name)))
           , lb = ifelse(conf.low < lim[1], "lower"
                         , ifelse(conf.high > lim[2], "upper", "neither"))
           , conf.low2 = ifelse(conf.low < lim[1], lim[1], conf.low)
           , conf.high2 = ifelse(conf.high > lim[2], lim[2], conf.high)
           , est = ifelse(Trait != " ", sprintf("%s [%s, %s]", estimate_f, conf.low_f, conf.high_f), "")
           ) %>% arrange(Trait)
  p1 <- df %>%
    ggplot(aes(x = Trait, y = estimate)) + 
    geom_errorbar(aes(ymin = conf.low2, ymax = conf.high2)
                  , position = "dodge"
                  , width = 0) + 
    geom_point(aes(shape = term, size = term)) +
    geom_segment(data = df %>% filter(lb == "lower")
                 , aes(y = conf.high2, yend = conf.low2, xend = Trait)
                 , arrow = arrow(type = "closed", length = unit(0.1, "cm"))) +
    geom_segment(data = df %>% filter(lb == "upper")
                 , aes(y = conf.low2, yend = conf.high2, xend = Trait)
                 , arrow = arrow(type = "closed", length = unit(0.1, "cm"))) +
    geom_hline(aes(yintercept = 0), linetype = "dashed", size = .5) +
    geom_vline(aes(xintercept = length(trts) + .5)) +
    annotate("rect", xmin = length(trts) + .6, xmax = Inf, ymin = -Inf, ymax = Inf, fill = "white") +
    annotate("text", label = "b [CI]", x = length(trts) + .75, y = lim_high*.75, hjust = .5, vjust = 0, fontface = 2, size = 3) +
    annotate("text", label = trm, x = length(trts) + .75, y = 0, hjust = .5, vjust = 0, fontface = 2, size = 3) +
    geom_text(aes(y = lim_high*.75, label = est), size = 3.5) +
    scale_y_continuous(limits = c(lim[1], lim_high), breaks = brk, labels = lab) + 
    scale_size_manual(values = c(3,2)) + 
    scale_shape_manual(values = c(15, 16)) +
    labs(x = NULL
         , y = "Estimate"
         # , title = meth
    ) +
    coord_flip() + 
    theme_classic() + 
    theme(legend.position = "none"
          , axis.text = element_text(face = "bold")
          , axis.title = element_text(face = "bold")
          , plot.title = element_text(face = "bold", hjust = .5)
          , axis.ticks.y = element_blank()
          , axis.line.y = element_blank()
          , axis.line.x.top = element_line(size = 1)
          # , panel.background = element_rect(fill = "transparent", colour = NA)
          # , plot.background = element_rect(fill = "transparent", colour = NA)
          )
  
  my_theme <- function(...) {
    theme_classic() + 
      theme(plot.title = element_text(face = "italic"))
  }
  title_theme <- calc_element("plot.title", my_theme())
  ttl <- ggdraw() + 
      draw_label(
          str_wrap(meth, 50),
          fontfamily = title_theme$family,
          fontface = title_theme$face,
          size = title_theme$size-2
      )
  p <- cowplot::plot_grid(ttl, p1, rel_heights = c(.15, .85), nrow = 2)
  return(p)  
}

nested_ipd_fx_fig <- nested_ipd_fx %>%
  unnest(fx) %>%
  filter((Moderator == "none" & term == "p_value") |
         (Moderator != "none" & grepl("p_value:", term)
          & !grepl("p_value:study", term)
          & !(grepl("cor_", term) | grepl("sd_", term)))) %>%
  # filter(!Moderator %in% unique(stdyModers$short_name)) %>%
  filter(!Moderator %in% c("scale", "continent", "country")) %>%
  mutate(sig = ifelse(sign(conf.low) == sign(conf.high), "sig", "ns"),
         Outcome = factor(Outcome, outcomes$short_name, outcomes$long_name),
         Covariate = factor(Covariate, covars$short_name, str_wrap(covars$long_name, 15)),
         term = str_remove_all(term, "p_value:"),
         term = str_replace(term, "metamod", Moderator),
         term = factor(term, c(covars$short_term, moders$short_term, stdyModers$short_term),
                       c(covars$long_term, moders$long_term, stdyModers$long_term)),
         Moderator = factor(Moderator, c(moders$short_name, stdyModers$short_name)
                            , c(moders$long_name, stdyModers$long_name))) %>%
  group_by(type, Moderator, Covariate, method, Outcome) %>%
  nest() %>%
  ungroup() %>%
  mutate(p = pmap(list(data, Outcome, Moderator, type, Covariate, method), possibly(fx_forest_fun, NA_real_)))

fx_forest_comb_fun <- function(d, type, out, mod, cov){
  m <- mapvalues(mod, c(moders$long_name, stdyModers$long_name), c(moders$short_name, stdyModers$short_name), warn_missing = F)
  o <- mapvalues(out, outcomes$long_name, outcomes$short_name, warn_missing = F)
  cv <- mapvalues(cov, covars$long_name, covars$short_name, warn_missing = F)
  p1 <- plot_grid(plotlist = d$p
            , nrow = ceiling(nrow(d)/2))
  titl <- if(mod == "None") sprintf("Personality-%s Associations", out) else sprintf("%s Moderators of Personality x %s Associations", mod, out)
  titl <- str_wrap(if(grepl("djust", cov)) sprintf("%s: %s %s %s", out, cov, type, titl) else sprintf("%s: %s Adjusted %s %s", out, cov, type, titl), 60)
  my_theme <- function(...) {
    theme_classic() + 
      theme(plot.title = element_text(face = "bold"))
  }
  title_theme <- calc_element("plot.title", my_theme())
  ttl <- ggdraw() + 
      draw_label(
          titl,
          fontfamily = title_theme$family,
          fontface = title_theme$face,
          size = title_theme$size-1
      )
  p <- cowplot::plot_grid(ttl, p1, rel_heights = c(.1, .9), nrow = 2)

  ht <- nrow(d)
  ggsave(file = sprintf("%s/results/figures/cross-method/overall forest/%s_%s_%s_%s_fixed.png"
                        , local_path, o, type, m, cv)
         , width = 10, height = ht*1.5)
  ggsave(file = sprintf("%s/results/figures/cross-method/overall forest/%s_%s_%s_%s_fixed.pdf"
                        , local_path, o, type, m, cv)
         , width = 10, height = ht*1.5)
  rm(p)
  gc()
  return(T)
}

nested_ipd_fx_fig <- nested_ipd_fx_fig %>%
  group_by(type, Outcome, Moderator, Covariate) %>%
  nest() %>% 
  ungroup() %>%
  mutate(p = pmap(list(data, type, Outcome, Moderator, Covariate), fx_forest_comb_fun))

include_graphics("https://github.com/emoriebeck/data-synthesis-tutorial/raw/main/results/figures/cross-method/overall%20forest/crystallized_Frequentist_none_all_fixed.pdf")

7.1.2.2 Study-Specific Estimates

loadRData <- function(fileName, type, method, obj){
#loads an RData file, and returns it
    # print(paste(type, method, fileName, dir, obj))
    path <- sprintf("%s/results/%s/%s/figures/study specific forest/rdata/%s", local_path, method, type, fileName)
    load(path)
    get(ls()[ls() == obj])
}

nested_ipd_fp <- 
  crossing(type = c("Frequentist", "Bayesian")
         , method = c("2a_ipd_dc", "2b_ipd_mlm", "3_ipd_meta")) %>%
  mutate(file = pmap(list(method, type, local_path), ~list.files(sprintf("%s/results/%s/%s/figures/study specific forest/rdata", ..3, ..1, ..2)))) %>%
    # filter(type != "Bayesian") %>%
    unnest(file) %>%
    # filter(method == "3_ipd_meta" & type == "Frequentist") %>%
    mutate(p = pmap(list(file, type, method, "p"), loadRData)) %>%
    separate(file, c("Outcome", "Trait", "Moderator", "Covariate"), sep = "_") %>%
    mutate(Covariate = str_remove_all(Covariate, ".RData")) %>%
  filter(!Moderator %in% stdyModers$short_name) %>%
  left_join(
    nested_ipd_rx %>%
      unnest(rx) %>%
      mutate(term = ifelse(is.na(term), names, term)) %>%
      filter((Moderator == "none" & term == "p_value") |
             (Moderator != "none" & grepl("p_value:", term))) %>%
      mutate(study = mapvalues(study, c("BASEI", "OCTOTWIN"), c("BASE-I", "OCTO-TWIN")),
             study = mapvalues(study, c("BASE-I", "OCTO-TWIN"), c("BASE", "OCTO-Twin"))) %>%
      group_by(type, method, Outcome, Trait, Moderator, Covariate) %>%
      summarize(nstd = n()) %>%
      ungroup()
  )

ipd_study_fp_fun <- function(d, outcome, cov, mod, type){
  print(paste(outcome, cov, mod, type))
  o <- mapvalues(outcome, outcomes$short_name, outcomes$long_name, warn_missing = F)
  cv <- mapvalues(cov, covars$short_name, covars$long_name, warn_missing = F)
  md <- mapvalues(mod, moders$short_name, moders$long_name, warn_missing = F)
  titl <- paste0(o, ",")
  titl <- if(!cov %in% c("none", "all")) paste(titl, cv, "Adjusted", collapse = ", ") else paste(titl, cv, collapse = ", ")
  ns <- d %>% group_by(method) %>% mutate(nstd = ((nstd + 2))/sum(nstd+2)) %>% group_by(Trait) %>% summarize(nstd = mean(nstd))
  # + theme(panel.background = element_rect(fill = "transparent", colour = NA),  plot.background = element_rect(fill = "transparent", colour = NA))
  my_theme <- function(...) {
    theme_classic() + 
      theme(plot.title = element_text(face = "bold.italic"))
  }
  title_theme <- calc_element("plot.title", my_theme())
  p1 <- plot_grid(
    d$p[[1]]  
    , d$p[[2]]
    , d$p[[3]]
    , d$p[[4]]
    , d$p[[5]]
    , nrow = 5
    , ncol = 1
    , rel_heights = ns$nstd
    , axis = "tblr"
    , align = "hv"
    )
  ttl <- ggdraw() + 
         draw_label(
          str_wrap(mthds$long_name[3], 40),
          fontfamily = title_theme$family,
          fontface = title_theme$face,
          size = title_theme$size 
      )
  p1 <- plot_grid(
    ttl, p1, rel_heights = c(.05, .95), ncol = 1
  )
  
  p2 <- plot_grid(
    d$p[[6]]
    , d$p[[7]]
    , d$p[[8]]
    , d$p[[9]]
    , d$p[[10]]
    , nrow = 5
    , ncol = 1
    , rel_heights = ns$nstd
    , axis = "tblr"
    , align = "hv"
  )
  ttl <- ggdraw() + 
         draw_label(
          str_wrap(mthds$long_name[4], 40),
          fontfamily = title_theme$family,
          fontface = title_theme$face,
          size = title_theme$size
      )
  p2 <- plot_grid(
    ttl, p2, rel_heights = c(.05, .95), ncol = 1
  )
  
  p3 <- plot_grid(
    d$p[[11]]
    , d$p[[12]]
    , d$p[[13]]
    , d$p[[14]] 
    , d$p[[15]]
    , nrow = 5
    , ncol = 1
    , rel_heights = ns$nstd
    , axis = "tblr"
    , align = "hv"
  )
  ttl <- ggdraw() + 
         draw_label(
          str_wrap(mthds$long_name[5], 40),
          fontfamily = title_theme$family,
          fontface = title_theme$face,
          size = title_theme$size 
      )
  p3 <- plot_grid(
    ttl, p3, rel_heights = c(.05, .95), ncol = 1
  )
  
  p <- plot_grid(
    p1, p2, p3
    , ncol = 3
  )
  
  my_theme <- function(...) {
    theme_classic() + 
      theme(plot.title = element_text(face = "bold", size = rel(1.8)))
  }
  
  title_theme <- calc_element("plot.title", my_theme())
  
  ttl <- ggdraw() + 
         draw_label(
          str_wrap("Point Estimates Are Quite Consistent Across Methods, While Confidence Intervals Vary Slightly Across Methods, Especially for Methods 2A and 3 versus 2B", 80),
          fontfamily = title_theme$family,
          fontface = title_theme$face,
          size = title_theme$size 
      )
  p <- plot_grid(
    ttl, p, rel_heights = c(.05, .95), ncol = 1
  )
  
  ggsave(p, 
         file = sprintf("%s/results/figures/cross-method/study-specific forest/%s-%s-%s-%s.png", local_path, type, outcome, mod, cov)
         , width = 14
         , height = 14)
  ggsave(p, 
         file = sprintf("%s/results/figures/cross-method/study-specific forest/%s-%s-%s-%s.pdf", local_path, type, outcome, mod, cov)
         , width = 14
         , height = 14)
  return(p)
}

nested_ipd_fp_comb <- nested_ipd_fp %>%
  mutate(Trait = factor(Trait, traits$short_name)) %>%
  arrange(type, method, Outcome, Trait, Moderator, Covariate) %>%
  group_by(type, Outcome, Moderator, Covariate) %>%
  nest() %>%
  ungroup() %>%
  # filter(type == "Frequentist") %>%
  mutate(p = pmap(list(data, Outcome, Covariate, Moderator, type), ipd_study_fp_fun))

tmp <- nested_ipd_fp_comb %>% filter(type == "Frequentist" & Covariate == "all")
for(i in 1:4){
  cat("#####", as.character(tmp$Moderator[[i]]), "\n\n")
  print(tmp$p[[i]])
}

7.1.2.3 Overall Simple Effects

loadRData <- function(fileName, type, method, obj, dir){
#loads an RData file, and returns it
    path <- sprintf("%s/results/%s/%s/%s/%s", local_path, method, type, dir, fileName)
    # print(path)
    load(path)
    get(ls()[grepl(obj, ls())])
}

nested_simp_fx <-
  crossing(type = c("Frequentist", "Bayesian")
         , method = c("1a_ipd_reg", "1b_ipd_fixef", "2a_ipd_dc", "2b_ipd_mlm", "3_ipd_meta")) %>%
  mutate(dirfx = ifelse(method != "3_ipd_meta", "predicted", "metaPredicted")
         , dirrx = ifelse(method != "3_ipd_meta", "predicted", "studyPredicted")
         , file = pmap(list(method, type, dirfx, local_path), ~list.files(sprintf("%s/results/%s/%s/%s", ..4, ..1, ..2, ..3)))) %>%
  unnest(file) %>%
  # filter(method == "3_ipd_meta") %>%
  mutate(pred.fx = pmap(list(file, type, method, "pred.fx", dirfx), possibly(loadRData, NA_real_))#,
         # pred.rx = pmap(list(file, type, method, "pred.rx", dirrx), possibly(loadRData, NA_real_))
         ) %>%
  separate(file, c("Outcome", "Trait", "Moderator", "Covariate"), sep = "_") %>%
  mutate(Covariate = str_remove_all(Covariate, ".RData"))

pred_fx_prep_fun <- function(d, mod, method){
  # print(paste(mod, method))
  if(method == "3_ipd_meta" & mod %in% moders$short_name) 
    return(d)
  else 
    d <- d %>% unclass %>% data.frame
    d$mod_value <- d[,mod]
    d <- d %>% select(-all_of(mod)) %>% as_tibble
    if(class(d$mod_value) %in% c("factor", "character")){d <- d %>% mutate(mod_fac = factor(mod_value))} 
    else {
      if(mod == "age") d <- d %>% mutate(mod_fac = factor(mod_value, levels = c(-10, 0, 10), labels = c("-10 yrs", "M", "+10 yrs")))
      else if(mod == "baseYear") d <- d %>% mutate(mod_fac = factor(mod_value, levels = c(-10, 0, 10), labels = c("1990", "200)0", "2010")))
      else if(mod == "baseAge") d <- d %>% mutate(mod_fac = factor(mod_value, levels = c(-10, 0, 10), labels = c("50", "60", "70")))
      else if(mod == "predInt") d <- d %>% mutate(mod_fac = factor(mod_value, levels = c(-5, 0, 5), labels = c("-5 yrs", "5 yrs", "+5 yrs")))
      else if(mod == "education") d <- d %>% mutate(mod_fac = factor(mod_value, levels = c(-5, 0, 5), labels = c("-5 yrs", "12 years", "+5 yrs")))
      else d <- d %>% mutate(mod_fac = factor(mod_value, levels = unique(mod_value), labels = c("-1 SD", "M", "+1 SD")))
    }
  d %>%
    group_by(p_value, mod_fac) %>%
    summarize_at(vars(one_of(c("pred", "lower", "upper"))), mean) %>%
    ungroup() 
}

nested_simp_fx <- nested_simp_fx %>%
  # filter(Moderator == "baseAge" & type == "Frequentist" & method == "3_ipd_meta") %>%
  mutate(pred.fx = pmap(list(pred.fx, Moderator, method), pred_fx_prep_fun))

ipd_se_plot_fun <- function(d, outcome, mod, cov, type){
  print(paste(mod, cov, type, outcome))
  o <- mapvalues(outcome, outcomes$short_name, outcomes$long_name, warn_missing = F)
  cv <- mapvalues(cov, covars$short_name, covars$long_name, warn_missing = F)
  m <- mapvalues(mod, c(moders$short_name, stdyModers$short_name), c(moders$long_name, stdyModers$long_name), warn_missing = F)
  titl <- if(mod == "none"){sprintf("%s", o)} else {sprintf("%s: Personality x %s Simple Effects", o, m)}
  # lt <- c("dotted", "solid", "dashed")[1:length(unique(d$mod_fac))]
  ht <- length(unique(d$mod_fac))
  mini <- floor(min(d$pred)); maxi <- 10
  p <- d %>% 
    mutate(Trait = factor(Trait, levels = traits$short_name)#, labels = traits$long_name)
           , method = mapvalues(method, mthds$old_name, str_wrap(mthds$long_name, 28), warn_missing = F)
           , lower = ifelse(lower < mini, mini, lower)
           , upper = ifelse(upper > maxi, maxi, upper)) %>%
    ggplot(aes(x = p_value, y = pred, group = interaction(Trait, mod_fac), linetype = mod_fac)) + 
      geom_line(aes(#color = mod_fac
                    , group = mod_fac
                    , linetype = mod_fac)
                , size = .75) +
      geom_ribbon(aes(fill = mod_fac
                      , group = mod_fac
                      , ymin = lower
                      , ymax = upper)
                  , alpha = .25) +
      facet_grid(Trait~method, scales = "free") + 
      scale_y_continuous(limits = c(mini,maxi)
                         , breaks = seq(mini, maxi, by = 2)
                         , labels = seq(mini, maxi, by = 2)) +
      # scale_color_manual(values = cols) +
      # scale_linetype_manual(values = lt) +
      labs(x = "Personality Score (POMP)"
           , y = "Cognition Score (POMP)"
           # , color = m
           , fill = m
           , linetype = m
           , title = titl
           # , subtitle = "Method 3: Two-Stage Individual Participant Meta-Analysis"
           )  +
      theme_classic() + 
      theme(legend.position = "bottom"
            , plot.title = element_text(face = "bold", size = rel(1.2), hjust = .5)
            , plot.subtitle = element_text(size = rel(1.1), hjust = .5)
            , strip.background = element_rect(fill = "black")
            # , strip.background.y = element_rect(fill = "white", color = "white")
            , strip.text.x = element_text(face = "bold", color = "white", size = rel(1))
            , strip.text.y = element_text(face = "bold", color = "white", size = rel(1))#, angle = 0)
            , axis.text = element_text(color = "black"))
  local_path <- length(unique(d$method))*2
  ggsave(p, file = sprintf("%s/results/figures/cross-method/overall simple effects/%s_%s_%s_%s.png", local_path, type, outcome, mod, cov)
         , width = local_path, height = 7)
  ggsave(p, file = sprintf("%s/results/figures/cross-method/overall simple effects/%s_%s_%s_%s.pdf", local_path, type, outcome, mod, cov)
         , width = local_path, height = 7)
  return(p)
}

nested_simp_fx_fp <- nested_simp_fx %>%
  filter(!(method %in% c("1b_ipd_fixef", "2a_ipd_dc") & Moderator %in% stdyModers$short_name)) %>%
  group_by(type, Outcome, Moderator, Covariate) %>%
  nest() %>% 
  ungroup() %>%
  mutate(data = map(data, ~(.) %>% unnest(pred.fx))
         , p = pmap(list(data, Outcome, Moderator, Covariate, type), ipd_se_plot_fun))

7.1.2.4 Study-Specific Simple Effects

loadRData <- function(fileName, type, method, obj, dir){
#loads an RData file, and returns it
    path <- sprintf("%s/results/%s/%s/%s/%s", local_path, method, type, dir, fileName)
    # print(path)
    load(path)
    get(ls()[grepl(obj, ls())])
}

nested_simp_rx <-
  crossing(type = c("Frequentist", "Bayesian")
         , method = c("2a_ipd_dc", "2b_ipd_mlm", "3_ipd_meta")) %>%
  mutate(dir = ifelse(method != "3_ipd_meta", "predicted", "studyPredicted")
         , file = pmap(list(method, type, dir, local_path), ~list.files(sprintf("%s/results/%s/%s/%s", ..4, ..1, ..2, ..3)))) %>%
  unnest(file) %>%
  # filter(method == "3_ipd_meta") %>%
  mutate(pred.rx = pmap(list(file, type, method, "pred.rx", dir), loadRData)) %>%
  separate(file, c("Outcome", "Trait", "Moderator", "Covariate", "study"), sep = "_") %>%
    mutate(study = str_remove_all(study, ".RData")
           , Covariate = str_remove_all(Covariate, ".RData")) %>%
  filter(!Moderator %in% stdyModers$short_name & Moderator != "SRhealth") %>%
  mutate(pred.rx = ifelse(!is.na(study), map2(pred.rx, study, ~(.x) %>% mutate(study = .y)), pred.rx)) %>%
  select(-study,  -dir) 

pred_rx_prep_fun <- function(d, mod){
  d <- d %>% unclass %>% data.frame
  d$mod_value <- d[,mod]
  d <- d %>% select(-all_of(mod)) %>% as_tibble
  if(class(d$mod_value) %in% c("factor", "character")){
    d <- d %>% mutate(mod_fac = factor(mod_value))
  } else{
    d2 <- d %>% 
        select(study, mod_value) %>% 
        distinct() %>% 
        arrange(study, mod_value)
    if(mod == "age") d2 <- d2 %>% mutate(mod_fac = factor(mod_value, levels = c(-10, 0, 10), labels = c("-10 yrs", "M", "+10 yrs")))
    else if(mod == "baseYear") d2 <- d2 %>% mutate(mod_fac = factor(mod_value, levels = c(-10, 0, 10), labels = c("1990", "200)0", "2010")))
    else if(mod == "baseAge") d2 <- d2 %>% mutate(mod_fac = factor(mod_value, levels = c(-10, 0, 10), labels = c("50", "60", "70")))
    else if(mod == "predInt") d2 <- d2 %>% mutate(mod_fac = factor(mod_value, levels = c(-5, 0, 5), labels = c("-5 yrs", "5 yrs", "+5 yrs")))
    else if(mod == "education") d2 <- d2 %>% mutate(mod_fac = factor(mod_value, levels = c(-5, 0, 5), labels = c("-5 yrs", "12 years", "+5 yrs")))
    else d2 <- d2 %>% mutate(mod_fac = factor(mod_value, levels = unique(mod_value), labels = c("-1 SD", "M", "+1 SD")))
    d <- d %>% full_join(d2) %>% ungroup()
  }
  d %>% 
    group_by(study, mod_fac, p_value) %>% 
    summarize_at(vars(one_of(c("pred", "lower", "upper"))), mean) %>%
    ungroup() 
}

nested_simp_rx <- nested_simp_rx %>%
  unnest(pred.rx) %>%
  group_by(type, Outcome, Trait, Moderator, Covariate) %>%
  nest(pred.rx = p_value:upper) %>%
  ungroup() %>%
  mutate(pred.rx = map2(pred.rx, Moderator, pred_rx_prep_fun))

ipd_std_se_plot_fun <- function(df, outcome, trait, mod, cov, type){
  print(paste(outcome, mod))
  o <- mapvalues(outcome, outcomes$short_name, outcomes$long_name, warn_missing = F)
  trt <- mapvalues(trait, traits$short_name, traits$long_name, warn_missing = F)
  cv <- mapvalues(cov, covars$short_name, covars$long_name, warn_missing = F)
  m <- mapvalues(mod, moders$short_name, moders$long_name, warn_missing = F)
  d <- round(max(abs(min(df$pred)), abs(max(df$pred))), 3)
  titl <- if(mod == "none"){sprintf("%s: %s", o, trt)} else {sprintf("%s: %s x %s Simple Effects", o, trt, m)}
  std <- unique(df$study)
  cols <- (stdcolors %>% filter(studies %in% std))$colors
  lt <- (stdcolors %>% filter(studies %in% std))$lt
  ht <- length(unique(df$mod_fac))
  mini <- if(min(df$pred) > 0) floor(min(df$pred)) else 0; maxi <- 10
  p <- df %>%
    filter(!is.na(study)) %>%
    mutate(study = factor(study, levels = stdcolors$studies),
           method = mapvalues(method, mthds$old_name, str_wrap(mthds$long_name, 25), warn_missing = F),
           # lower = ifelse(lower < 4, 4, lower),
           # upper = ifelse(upper > 10, 10, upper),
           gr = ifelse(study == "Overall", "Overall", "study")) %>%
    group_by(study, mod_fac, p_value, gr, method) %>%
    summarize_at(vars(pred, lower, upper), mean) %>%
    ungroup() %>%
    ggplot(aes(x = p_value
               , y = pred
               , group  = study))  +
      scale_y_continuous(limits = c(mini,maxi)
                         , breaks = seq(mini, maxi, by = 2)
                         , labels = seq(mini, maxi, by = 2)) +
      scale_linetype_manual(values = lt) +
      scale_color_manual(values = cols) +
      scale_fill_manual(values = cols) +
      scale_size_manual(values = c(2,.8)) + 
      geom_line(aes(linetype = study, color = study, size = gr)) +
      labs(x = "Personality (POMP)"
           , y = paste(o, "(POMP)")
           , title = titl
           , linetype = "Study"
           , color = "Study"
           , fill = "Study"
           # , subtitle = "Method 2B: Pooled Regression Using Random Effects"
           ) +
      guides(size = "none") +
      facet_grid(mod_fac ~ method, scales = "free") +
      theme_classic() +
      theme(legend.position = "bottom"
            , plot.title = element_text(face = "bold", size = rel(1.2), hjust = .5)
            # , plot.subtitle = element_text(size = rel(1.1), hjust = .5)
            , strip.background = element_rect(fill = "black", color = "black")
            , panel.background = element_rect(color = "black")
            , strip.text = element_text(face = "bold", color = "white")
            , axis.text = element_text(color = "black"))
  ggsave(p, file = sprintf("%s/results/figures/cross-method/study specific simple effects/%s_%s_%s_%s_%s.png", local_path, type, outcome, trt, mod, cov), width = 8, height = 3*ht)
  ggsave(p, file = sprintf("%s/results/figures/cross-method/study specific simple effects/%s_%s_%s_%s_%s.pdf", local_path, type, outcome, trt, mod, cov), width = 8, height = 3*ht)
  return(p)
}

nested_simp_fx %>%
  select(-contains("dir")) %>%
  right_join(nested_simp_rx %>% 
               mutate(pred.rx = map(pred.rx
               , ~(.) %>% mutate(study = mapvalues(
                 study, c("OCTOTWIN", "OCTO-TWIN", "BASEI", "BASE-I")
                 , c("OCTO-Twin", "OCTO-Twin", "BASE", "BASE")
                 , warn_missing = F))
             ))) %>%
  filter(!map_lgl(pred.fx, is.null)) %>%
  mutate(pred.comb = map2(pred.fx, pred.rx, ~(.x) %>% mutate(study = "Overall") %>% full_join(.y))) %>%
  select(-pred.fx, -pred.rx) %>%
  group_by(type, Outcome, Trait, Moderator, Covariate) %>%
  nest() %>%
  ungroup() %>%
  # filter(type == "Frequentist" & Moderator == "gender" & Trait == "E") %>%
  mutate(data = map(data, ~(.) %>% unnest(pred.comb))
         , pmap(list(data, Outcome, Trait, Moderator, Covariate, type), ipd_std_se_plot_fun))

7.2 Comparisons Across Methods: Bayesian versus Frequentist

7.2.1 Tables

7.2.1.1 Fixed Effects

## table function 
ipd_comp_fx_tab_fun <- function(d, moder, covar){
  print(moder)
  md <- mapvalues(moder, c(moders$long_name, stdyModers$long_name), c(moders$short_name, stdyModers$short_name), warn_missing = F)
  cv <- mapvalues(covar, covars$long_name, covars$short_name)
  rs <- d %>% mutate(method = factor(method, levels = mthds$old_name, labels = mthds$long_name)) %>% group_by(method) %>% tally() %>% 
    mutate(end = cumsum(n), start = lag(end) + 1, start = ifelse(is.na(start), 1, start))
  cs <- if(length(unique(d$term)) == 1) c(1, rep(2,5)) else rep(2,6)
  names(cs) <- c(" ", traits$short_name)
  cln <- if(length(unique(d$term)) == 1) c(" ", rep(c("<em>b</em>", "CI"), times = 5)) else c(" ", "Term", rep(c("<em>b</em>", "[CI]"), times = 5))
  al <- if(length(unique(d$term))) c("r", rep("c", 10)) else c("r", "r", rep("c", 10))
  if(length(unique(d$term)) == 1) {
    d <- d %>% select(-term)
  } 
  cap <- if(md == "none") "Comparison of Bayesian and Frequentist Approaches to Overall Effects of Personality-Crystallized Domain Associations" else sprintf("Comparison of Bayesian and Frequentist Approaches to Overall %s Moderation of Personality-Crystallized Domain Associations", md)
  tab <- d %>%
    select(-method) %>%
    kable(., "html"
          , escape = F
          , col.names = cln
          , align = al
          , caption = cap
    ) %>% 
    kable_classic(full_width = F, html_font = "Times New Roman") %>%
    add_header_above(cs) %>%
    collapse_rows(1, valign = "top", row_group_label_position = "stack")
  for (i in 1:nrow(rs)) {
    tab <- tab %>% kableExtra::group_rows(rs$method[i], rs$start[i], rs$end[i])
  }
  # if(dubs == T) for(i in 1:nrow(rs2)) {
  #   tab <- tab %>% kableExtra::group_rows(rs2$method[i], rs2$start[i], rs2$end[i]
  #                                         , indent = T, hline_after = F)
  # }
  save_kable(tab, file = sprintf("%s/results/tables/bayes-v-freq/overall/%s_%s.html"
                                 , local_path, md, cv))
  return(tab)
}

nested_comp_fx_tab <- ipd_fx_tab %>% 
  group_by(Moderator, Covariate, Outcome) %>%
  arrange(method, type) %>%
  nest() %>%
  ungroup() %>%
  mutate(tab = pmap(list(data, Moderator, Covariate), ipd_comp_fx_tab_fun))

7.2.1.2 Study-Specific

ipd_rx_comp_tab_fun <- function(d, moder, covar){
  print(moder)
  md <- mapvalues(moder, c(moders$long_name, stdyModers$long_name), c(moders$short_name, stdyModers$short_name), warn_missing = F)
  cv <- mapvalues(covar, covars$long_name, covars$short_name)
  rs <- d %>% mutate(method = factor(method, levels = mthds$old_name, labels = mthds$long_name)) %>% group_by(method) %>% tally() %>% 
    mutate(end = cumsum(n), start = lag(end) + 1, start = ifelse(is.na(start), 1, start))
  cs <- if(length(unique(d$term)) == 1) rep(2,6) else c(3, rep(2,5))
  names(cs) <- c(" ", traits$short_name)
  cln <- if(length(unique(d$term)) == 1) c(" ", "Study", rep(c("<em>b</em>", "CI"), times = 5)) else c(" ", "Study", "Term", rep(c("<em>b</em>", "[CI]"), times = 5))
  al <- if(length(unique(d$term))) c("r", "r", rep("c", 10)) else c("r", "r", "r", rep("c", 10))
  if(length(unique(d$term)) == 1) {
    d <- d %>% select(-term); dubs <- F
  } #else {
  #   rs2 <- d %>% group_by(Covariate, method) %>% tally() %>% 
  #   mutate(end = cumsum(n), start = lag(end) + 1, start = ifelse(is.na(start), 1, start))
  #   d <- d %>% select(-method); dubs <- T
  # }
  # caption 
  cap <- if(md == "none") "Comparison of Bayesian and Frequentist Approaches to Personality-Crystallized Domain Associations" else sprintf("Comparison of Bayesian and Frequentist Approaches to Study-Specific %s Moderation of Personality-Crystallized Domain Associations", md)
  tab <- d %>%
    select(study, type, everything(), -method) %>%
    kable(., "html"
          , escape = F
          , booktabs = T
          , col.names = cln
          , align = al
          , caption = cap
    ) %>% 
    kable_classic(full_width = F, html_font = "Times New Roman") %>%
    add_header_above(cs) %>% 
    collapse_rows(1:2, valign = "top", row_group_label_position = "stack")
  for (i in 1:nrow(rs)) {
    tab <- tab %>% kableExtra::group_rows(rs$method[i], rs$start[i], rs$end[i])
  }
  # if(dubs == T) for(i in 1:nrow(rs2)) {
  #   tab <- tab %>% kableExtra::group_rows(rs2$method[i], rs2$start[i], rs2$end[i]
  #                                         , indent = T, hline_after = F)
  # }
  save_kable(tab, file = sprintf("%s/results/tables/bayes-v-freq/study-specific/%s_%s.html"
                                 , local_path, md, cv, md))
  return(tab)
}

nested_comp_fx_tab <- ipd_rx_tab %>% 
  mutate(study = mapvalues(study, c("BASEI", "OCTOTWIN"), c("BASE-I", "OCTO-TWIN"))) %>%
  group_by(Moderator, Covariate, Outcome) %>%
  arrange(method, study, type) %>%
  nest() %>%
  ungroup() %>%
  mutate(tab = pmap(list(data, Moderator, Covariate), ipd_rx_comp_tab_fun))

7.2.2 Figures

7.2.2.1 Fixed Effects

fx_forest_fun <- function(d, mod, type, cov){
  print(paste(mod, cov))
  m <- mapvalues(mod, moders$long_name, moders$short_name, warn_missing = F)
  cv <- mapvalues(cov, covars$long_name, covars$short_name, warn_missing = F)
  d <- d %>% filter(!is.na(estimate))
  dl <- round(max(abs(min(d$estimate)), abs(max(d$estimate))), 3)
  dig <- if(dl < .01) 3 else 2
  lim <- if(mod == "none"){c(-.25, .25)} else{c(round_any(0-dl-(dl/2.5), .001, floor), round_any(0+dl+(dl/2.5), .001, ceiling))}
  brk <- if(mod == "none"){seq(-.2,.2,.2)} else{round(c(0-dl-(dl/5), 0, 0+dl+(dl/5)),3)}
  lab <- if(mod == "none"){c("-.2", "0", ".2")} else{round(c(0-dl-(dl/5), 0, 0+dl+(dl/5)),dig)}
  shapes <- c(15, 16)[1:length(unique(d$term))]
  lt <- rep("solid", length(unique(d$term)))
  titl <- if(m == "none"){NULL} else {sprintf("%s Moderation of Personality-Outcome Associations", mod)}
  titl <- if(!cv %in% c("none", "all")) paste(cov, "Adjusted", titl, collapse = " ") else paste(cov, titl, collapse = " ")
  leg <- if(length(unique(d$term)) > 1){"bottom"} else {"none"}
  p <- d %>%
    mutate(conf.low = ifelse(conf.low < lim[1], lim[1], conf.low),
           conf.high = ifelse(conf.high > lim[2], lim[2], conf.high)) %>% 
  ggplot(aes(x = method, y = estimate)) +
    scale_y_continuous(limits = lim, breaks = brk, labels = lab) + 
    scale_size_manual(values = c(1.3, .85)) +
    scale_shape_manual(values = shapes) +
    scale_color_manual(values = c("blue", "black")) +
    scale_linetype_manual(values = lt) +
    geom_hline(aes(yintercept = 0), size = .25, color = "gray50") +
    geom_errorbar(aes(ymin = conf.low, ymax = conf.high, linetype = term)
                  , width = 0
                  , position = position_dodge(width = .9)) + 
    geom_point(aes(color = sig, size = sig, shape = term)
                  , position = position_dodge(width = .9)) +
    labs(x = NULL, y = "Estimate (POMP)", title = titl) +
    facet_grid(Outcome~Trait, scales = "free_y", space = "free") +
    coord_flip() +
    theme_classic() +
    theme(legend.position = leg,
          plot.title = element_text(face = "bold", size = rel(1.2), hjust = .5),
          panel.background = element_rect(color = "black", fill = "white"),
          strip.background = element_blank(),
          strip.text = element_text(face = "bold", color = "black", size = rel(1.4)),
          axis.text = element_text(color = "black"),
          axis.text.y = element_text(size = rel(1)))
  ht <- length(unique(d$Outcome))
  local_path <- length(unique(d$Trait))
  ggsave(file = sprintf("%s/results/figures/bayes-v-freq/overall forest/%s_%s_%s_fixed.png", local_path, type, mod, cv), width = local_path*2, height = ht*3)
  gc()
  return(p)
}

nested_ipd_fx_fig <-
  nested_ipd_fx %>%
  unnest(fx) %>%
  filter((Moderator == "none" & term == "p_value") |
         (Moderator != "none" & grepl("p_value:", term)
          & !grepl("p_value:study", term)
          & !(grepl("cor_", term) | grepl("sd_", term)))) %>%
  # filter(!Moderator %in% unique(stdyModers$short_name)) %>%
  filter(!Moderator %in% c("scale", "continent", "country")) %>%
  mutate(sig = ifelse(sign(conf.low) == sign(conf.high), "sig", "ns"),
         Outcome = factor(Outcome, outcomes$short_name, outcomes$long_name),
         Covariate = factor(Covariate, covars$short_name, str_wrap(covars$long_name, 15)),
         term = str_remove_all(term, "p_value:"),
         term = ifelse(term == "gender", "genderFemale", term),
         term = str_replace(term, "metamod", Moderator),
         term = factor(term, c(covars$short_term, moders$short_term, stdyModers$short_term),
                       c(covars$long_term, moders$long_term, stdyModers$long_term)),
         Moderator = factor(Moderator, c(moders$short_name, stdyModers$short_name)
                            , c(moders$long_name, stdyModers$long_name))) %>%
  group_by(type, Moderator, Covariate) %>%
  nest() %>%
  ungroup() %>%
  # filter(Moderator == "Gender") %>%
  mutate(p = pmap(list(data, Moderator, type, Covariate), fx_forest_fun))

7.2.2.2 Study-Specific Effects

rx_forest_fun <- function(d, mod, type, cov, out){
  print(paste(mod, cov))
  m <- mapvalues(mod, moders$long_name, moders$short_name, warn_missing = F)
  cv <- mapvalues(cov, covars$long_name, covars$short_name, warn_missing = F)
  d <- d %>% filter(!is.na(estimate))
  dl <- round(max(abs(min(d$estimate)), abs(max(d$estimate))), 3)
  lim <- if(mod == "none"){c(-.25, .25)} else{c(0-dl-(dl/2.5), 0+dl+(dl/2.5))}
  brk <- if(mod == "none"){seq(-.2,.2,.2)} else{round(c(0-dl-(dl/5), 0, 0+dl+(dl/5)),2)}
  lab <- if(mod == "none"){c("-.2", "0", ".2")} else{str_remove(round(c(0-dl-(dl/5), 0, 0+dl+(dl/5)),2), "^0")}
  shapes <- c(15, 16)[1:length(unique(d$term))]
  lt <- rep("solid", length(unique(d$term)))
  titl <- if(m == "none"){NULL} else {sprintf("%s Moderation of Personality-Outcome Associations", mod)}
  titl <- if(!cv %in% c("none", "all")) paste(cov, "Adjusted", titl, collapse = " ") else paste(cov, titl, collapse = " ")
  leg <- if(length(unique(d$term)) > 1){"bottom"} else {"none"}
  p <- d %>%
    mutate(conf.low = ifelse(conf.low < lim[1], lim[1], conf.low),
           conf.high = ifelse(conf.high > lim[2], lim[2], conf.high),
           Trait = factor(Trait, levels = traits$short_name)) %>% 
  ggplot(aes(x = method, y = estimate)) +
    scale_y_continuous(limits = lim, breaks = brk, labels = lab) + 
    scale_size_manual(values = c(.85, 1.3)) +
    scale_shape_manual(values = shapes) +
    scale_color_manual(values = c("black", "blue")) +
    scale_linetype_manual(values = lt) +
    geom_hline(aes(yintercept = 0), size = .25, color = "gray50") +
    geom_errorbar(aes(ymin = conf.low, ymax = conf.high, linetype = term)
                  , width = 0
                  , position = position_dodge(width = .9)) + 
    geom_point(aes(color = sig, size = sig, shape = term)
                  , position = position_dodge(width = .9)) +
    labs(x = NULL, y = "Estimate (POMP)", title = titl) +
    facet_grid(Trait~study, scales = "free_y", space = "free") +
    coord_flip() +
    theme_classic() +
    theme(legend.position = leg,
          plot.title = element_text(face = "bold", size = rel(1.2), hjust = .5),
          panel.background = element_rect(color = "black", fill = "white"),
          strip.background = element_blank(),
          strip.text.y = element_text(face = "bold", color = "black", size = rel(1.4)),
          strip.text.x = element_text(face = "bold", color = "black", size = rel(1.3)),
          axis.text = element_text(color = "black"),
          axis.text.y = element_text(size = rel(1)))
  ht <- length(unique(d$Trait))
  local_path <- length(unique(d$study))
  ggsave(file = sprintf("%s/results/figures/bayes-v-freq/study-specific/%s_%s_%s_%s_fixed.png", local_path, type, out, mod, cv), width = local_path*1.5, height = ht*2)
  gc()
  return(p)
}

nested_ipd_rx_fig <- nested_ipd_rx %>% 
  unnest(rx) %>%
  mutate(term = ifelse(is.na(term), names, term)) %>%
  filter((Moderator == "none" & term == "p_value") |
         (Moderator != "none" & grepl("p_value:", term))) %>%
  mutate(sig = ifelse(sign(conf.low) == sign(conf.high), "sig", "ns"),
         Outcome = factor(Outcome, outcomes$short_name, outcomes$long_name),
         Covariate = factor(Covariate, covars$short_name, str_wrap(covars$long_name, 15)),
         term = str_remove_all(term, "p_value:"),
         term = ifelse(term == "gender", "genderFemale", term),
         term = factor(term, c(covars$short_term, moders$short_term, stdyModers$short_term),
                       c(covars$long_term, moders$long_term, stdyModers$long_term)),
         Moderator = factor(Moderator, c(moders$short_name, stdyModers$short_name)
                            , c(moders$long_name, stdyModers$long_name)),
         study = mapvalues(study, c("BASEI", "OCTOTWIN"), c("BASE-I", "OCTO-TWIN"))) %>%
  group_by(type, Moderator, Covariate, Outcome) %>% 
  nest() %>%
  ungroup() %>%
  mutate(p = pmap(list(data, Moderator, type, Covariate, Outcome), rx_forest_fun))