Explore SAPA data

Init

library(pacman)
p_load(kirkegaard, dplyr)

load("data/ICAR/sapaICARData18aug2010thru20may2013.rdata")
icar = sapaICARData18aug2010thru20may2013; rm(sapaICARData18aug2010thru20may2013)
load("data/personality/sapaTempData696items08dec2013thru26jul2014.RData")
pers = sapaTempData696items08dec2013thru26jul2014; rm(sapaTempData696items08dec2013thru26jul2014)

Sample size by country

icar$country %>% table2()

## # A tibble: 199 × 3
##    Group Count    Percent
##    <chr> <dbl>      <dbl>
## 1    USA 75740 78.1162978
## 2    CAN  4322  4.4576002
## 3    GBR  2082  2.1473215
## 4    AUS  1625  1.6759834
## 5    MYS  1466  1.5119949
## 6    IND   903  0.9313311
## 7    PHL   893  0.9210173
## 8    DEU   596  0.6146991
## 9    SWE   468  0.4826832
## 10   SGP   382  0.3939850
## # ... with 189 more rows

icar_items = str_subset(names(icar), "[A-Z0-9]+\\.\\d\\d")
country_CA = plyr::ddply(icar, "country", function(b) {
  #mean item correct
  mean_items = b[icar_items] %>% colMeans(na.rm = T)
  
  #mean correct
  mean_cor = mean(mean_items, na.rm = T)
  sd_cor = sd(mean_items, na.rm = T)
  
  data_frame(
    mean_score = mean_cor,
    sd_score = sd_cor,
    n = nrow(b)
  )
})

#inspect those with >50
country_CA %>% filter(n > 50) %>% arrange(-mean_score)

##    country mean_score  sd_score     n
## 1      NLD  0.6372274 0.2276223   210
## 2      TUR  0.6152418 0.2424665    90
## 3      CHE  0.6013322 0.2494151    72
## 4      BEL  0.5959513 0.2516541   106
## 5      FIN  0.5930721 0.2480195   145
## 6      DEU  0.5881822 0.2283739   596
## 7      FRA  0.5879127 0.2445763   216
## 8      POL  0.5785486 0.2299739   167
## 9      BGR  0.5720609 0.3324657    59
## 10     ITA  0.5663144 0.2672788   126
## 11     CZE  0.5618671 0.2734046    63
## 12     HRV  0.5562421 0.2950524    86
## 13     CHN  0.5539784 0.2408589   360
## 14     PRT  0.5509224 0.2936677    79
## 15     AUT  0.5455126 0.2517483    62
## 16     IRN  0.5405326 0.2787687    69
## 17     TWN  0.5372400 0.2716416    74
## 18     KOR  0.5361917 0.2539384   176
## 19     SGP  0.5335865 0.2483463   382
## 20     NZL  0.5303756 0.2453946   271
## 21     SWE  0.5188640 0.2209762   468
## 22     SRB  0.5172406 0.2619086   149
## 23     IDN  0.5132907 0.2801849   156
## 24     DNK  0.5119294 0.2458524   117
## 25     IRL  0.5073820 0.2698259   200
## 26     ARG  0.5014125 0.2858421    73
## 27     BRA  0.5001248 0.2445863   216
## 28     JPN  0.5000454 0.2838320   119
## 29     GBR  0.4976409 0.2566372  2082
## 30     RUS  0.4965564 0.2695398   120
## 31     ESP  0.4940054 0.2698945   102
## 32     AUS  0.4922487 0.2511292  1625
## 33     VNM  0.4895790 0.2497653    95
## 34     NOR  0.4875717 0.2335455   366
## 35     ROU  0.4857763 0.2635645   199
## 36     HKG  0.4831844 0.2737520   236
## 37     GRC  0.4769979 0.3003235    86
## 38     IND  0.4733728 0.2740179   903
## 39     ZAF  0.4672794 0.2828818   267
## 40     CAN  0.4640510 0.2430983  4322
## 41     THA  0.4563408 0.3139223    72
## 42     LBN  0.4504836 0.3274871    77
## 43     UKR  0.4456687 0.3047114    57
## 44     EGY  0.4366311 0.2937821    72
## 45     KEN  0.4258129 0.3018063    99
## 46     ARE  0.4228557 0.2970464    84
## 47     PRI  0.4192239 0.2528325    69
## 48     USA  0.4179486 0.2539949 75740
## 49     MEX  0.4176345 0.2586489   320
## 50     NGA  0.4157297 0.2963079   213
## 51     TTO  0.4068309 0.3304514    55
## 52     SAU  0.3970575 0.2835122    99
## 53     COL  0.3948141 0.2990252    92
## 54     JAM  0.3869677 0.2799748    91
## 55     PHL  0.3804804 0.2659989   893
## 56     MYS  0.3556474 0.2444668  1466
## 57     PAK  0.3541264 0.2508817   221
## 58     GHA  0.3441959 0.2770726    53
## 59     AFG  0.3151051 0.2547079    53