R Notebook

First, we got all data from the repository. You check the code below

ds <- step_processed

Then we realized that the number of cases were different

ds %>% count(country) %>% janitor::adorn_totals()

     country     n
     Armenia  2992
     Bolivia  2433
    Colombia  2617
     Georgia  2996
       Ghana  2987
       Kenya  3894
        Laos  2845
   Macedonia  4009
 Philippines  3000
      Serbia  3344
   Sri_Lanka  2989
     Ukraine  2389
     Vietnam  3405
      Yunnan  2017
       Total 41917

We found the same sampel size when filtering the missing cases in acquiescence_bias_cor (please see the code below):

#filtering the dataset
ds %>% 
  filter(!is.na(acquiescence_bias_cor)) -> step_published_ds

Now everything seems to be ok and we can check the Table S1. Descriptive statistics of STEP data. in the manuscript.

We also checked the range within all items:

And now we were confident to run the Cronbach’s alpha computation. But the values were not the same. We got 0.66, but in the manuscript this value was 0.49 (Table 2.)

#Alpha
step_published_ds %>% dplyr::select(step_bfi1_ab_cor:step_bfi39_ab_cor) %>% psych::alpha(.)

Matrix was not positive definite, smoothing was doneMatrix was not positive definite, smoothing was doneIn smc, smcs < 0 were set to .0
Matrix was not positive definite, smoothing was doneIn smc, smcs < 0 were set to .0
Matrix was not positive definite, smoothing was doneIn smc, smcs < 0 were set to .0
Matrix was not positive definite, smoothing was doneIn smc, smcs < 0 were set to .0
Matrix was not positive definite, smoothing was doneIn smc, smcs < 0 were set to .0
Matrix was not positive definite, smoothing was doneIn smc, smcs < 0 were set to .0
Matrix was not positive definite, smoothing was doneIn smc, smcs < 0 were set to .0
Matrix was not positive definite, smoothing was doneIn smc, smcs < 0 were set to .0

Reliability analysis   
Call: psych::alpha(x = .)

 

 lower alpha upper     95% confidence boundaries
0.66 0.66 0.67 

 Reliability if an item is dropped:

 Item statistics