World Values Survey (WVS)

Build Status Build status

The World Values Survey studies changing values and their impact on social and political life in almost one hundred nations.

  • One table per country per wave, with one row per sampled respondent.

  • A complex sample survey designed to generalize the population aged eighteen and older in participating countries.

  • Released about twice per decade since 1981.

  • Administered as a confederacy, guided by a scientific advisory committee and funded by consortium.

Simplified Download and Importation

The R lodown package easily downloads and imports all available WVS microdata by simply specifying "wvs" with an output_dir = parameter in the lodown() function. Depending on your internet connection and computer processing speed, you might prefer to run this step overnight.

library(lodown)
lodown( "wvs" , output_dir = file.path( path.expand( "~" ) , "WVS" ) )

lodown also provides a catalog of available microdata extracts with the get_catalog() function. After requesting the WVS catalog, you could pass a subsetted catalog through the lodown() function in order to download and import specific extracts (rather than all available extracts).

library(lodown)
# examine all available WVS microdata files
wvs_cat <-
    get_catalog( "wvs" ,
        output_dir = file.path( path.expand( "~" ) , "WVS" ) )

# wave six only
wvs_cat <- subset( wvs_cat , grepl( "United(.*)States" , full_url ) & wave == 6 )
# download the microdata to your local computer
lodown( "wvs" , wvs_cat )

Analysis Examples with the survey library

Construct a complex sample survey design:

library(survey)

wvs_df <-
    readRDS( 
        file.path( path.expand( "~" ) , "WVS" , 
            "wave 6/F00003106-WV6_Data_United_States_2011_spss_v_2016-01-01.rds" ) 
    )

# construct a fake survey design
warning( "this survey design produces correct point estimates
but incorrect standard errors." )
wvs_design <- 
    svydesign( 
        ~ 1 , 
        data = wvs_df , 
        weights = ~ v258
    )

Variable Recoding

Add new columns to the data set:

wvs_design <- 
    update( 
        wvs_design , 
        
        one = 1 ,
        
        language_spoken_at_home =
            factor( v247 , 
                levels = c( 101 , 128 , 144 , 208 , 426 , 800 ) , 
                labels = c( 'chinese' , 'english' , 'french' , 
                    'japanese' , 'spanish; castilian' , 'other' )
            ) ,

        citizen = as.numeric( v246 == 1 ) ,
        
        task_creativity_1_10 = as.numeric( v232 ) ,
        
        work_independence_1_10 = as.numeric( v233 ) ,
        
        family_importance =
            factor( v4 , 
                labels = c( 'very' , 'rather' , 'not very' , 'not at all' ) 
            )
    )

Unweighted Counts

Count the unweighted number of records in the survey sample, overall and by groups:

sum( weights( wvs_design , "sampling" ) != 0 )

svyby( ~ one , ~ language_spoken_at_home , wvs_design , unwtd.count )

Weighted Counts

Count the weighted size of the generalizable population, overall and by groups:

svytotal( ~ one , wvs_design )

svyby( ~ one , ~ language_spoken_at_home , wvs_design , svytotal )

Descriptive Statistics

Calculate the mean (average) of a linear variable, overall and by groups:

svymean( ~ task_creativity_1_10 , wvs_design , na.rm = TRUE )

svyby( ~ task_creativity_1_10 , ~ language_spoken_at_home , wvs_design , svymean , na.rm = TRUE )

Calculate the distribution of a categorical variable, overall and by groups:

svymean( ~ family_importance , wvs_design , na.rm = TRUE )

svyby( ~ family_importance , ~ language_spoken_at_home , wvs_design , svymean , na.rm = TRUE )

Calculate the sum of a linear variable, overall and by groups:

svytotal( ~ task_creativity_1_10 , wvs_design , na.rm = TRUE )

svyby( ~ task_creativity_1_10 , ~ language_spoken_at_home , wvs_design , svytotal , na.rm = TRUE )

Calculate the weighted sum of a categorical variable, overall and by groups:

svytotal( ~ family_importance , wvs_design , na.rm = TRUE )

svyby( ~ family_importance , ~ language_spoken_at_home , wvs_design , svytotal , na.rm = TRUE )

Calculate the median (50th percentile) of a linear variable, overall and by groups:

svyquantile( ~ task_creativity_1_10 , wvs_design , 0.5 , na.rm = TRUE )

svyby( 
    ~ task_creativity_1_10 , 
    ~ language_spoken_at_home , 
    wvs_design , 
    svyquantile , 
    0.5 ,
    ci = TRUE ,
    keep.var = TRUE ,
    na.rm = TRUE
)

Estimate a ratio:

svyratio( 
    numerator = ~ task_creativity_1_10 , 
    denominator = ~ work_independence_1_10 , 
    wvs_design ,
    na.rm = TRUE
)

Subsetting

Restrict the survey design to seniors:

sub_wvs_design <- subset( wvs_design , v242 >= 65 )

Calculate the mean (average) of this subset:

svymean( ~ task_creativity_1_10 , sub_wvs_design , na.rm = TRUE )

Measures of Uncertainty

Extract the coefficient, standard error, confidence interval, and coefficient of variation from any descriptive statistics function result, overall and by groups:

this_result <- svymean( ~ task_creativity_1_10 , wvs_design , na.rm = TRUE )

coef( this_result )
SE( this_result )
confint( this_result )
cv( this_result )

grouped_result <-
    svyby( 
        ~ task_creativity_1_10 , 
        ~ language_spoken_at_home , 
        wvs_design , 
        svymean ,
        na.rm = TRUE 
    )
    
coef( grouped_result )
SE( grouped_result )
confint( grouped_result )
cv( grouped_result )

Calculate the degrees of freedom of any survey design object:

degf( wvs_design )

Calculate the complex sample survey-adjusted variance of any statistic:

svyvar( ~ task_creativity_1_10 , wvs_design , na.rm = TRUE )

Include the complex sample design effect in the result for a specific statistic:

# SRS without replacement
svymean( ~ task_creativity_1_10 , wvs_design , na.rm = TRUE , deff = TRUE )

# SRS with replacement
svymean( ~ task_creativity_1_10 , wvs_design , na.rm = TRUE , deff = "replace" )

Compute confidence intervals for proportions using methods that may be more accurate near 0 and 1. See ?svyciprop for alternatives:

svyciprop( ~ citizen , wvs_design ,
    method = "likelihood" , na.rm = TRUE )

Regression Models and Tests of Association

Perform a design-based t-test:

svyttest( task_creativity_1_10 ~ citizen , wvs_design )

Perform a chi-squared test of association for survey data:

svychisq( 
    ~ citizen + family_importance , 
    wvs_design 
)

Perform a survey-weighted generalized linear model:

glm_result <- 
    svyglm( 
        task_creativity_1_10 ~ citizen + family_importance , 
        wvs_design 
    )

summary( glm_result )

Analysis Examples with srvyr

The R srvyr library calculates summary statistics from survey data, such as the mean, total or quantile using dplyr-like syntax. srvyr allows for the use of many verbs, such as summarize, group_by, and mutate, the convenience of pipe-able functions, the tidyverse style of non-standard evaluation and more consistent return types than the survey package. This vignette details the available features. As a starting point for WVS users, this code replicates previously-presented examples:

library(srvyr)
wvs_srvyr_design <- as_survey( wvs_design )

Calculate the mean (average) of a linear variable, overall and by groups:

wvs_srvyr_design %>%
    summarize( mean = survey_mean( task_creativity_1_10 , na.rm = TRUE ) )

wvs_srvyr_design %>%
    group_by( language_spoken_at_home ) %>%
    summarize( mean = survey_mean( task_creativity_1_10 , na.rm = TRUE ) )

Replication Example