Programme for the International Assessment of Adult Competencies (PIAAC)
The Programme for the International Assessment of Adult Competencies (PIAAC) offers cross-national comparisons for the serious study of advanced-nation labor markets.
One row per sampled adult.
A multiply-imputed, complex sample survey designed to generalize to the population aged 16 to 65 across thirty three OECD nations.
No expected release timeline.
Administered by the Organisation for Economic Co-operation and Development.
Simplified Download and Importation
The R lodown
package easily downloads and imports all available PIAAC microdata by simply specifying "piaac"
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( "piaac" , output_dir = file.path( path.expand( "~" ) , "PIAAC" ) )
lodown
also provides a catalog of available microdata extracts with the get_catalog()
function. After requesting the PIAAC 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 PIAAC microdata files
piaac_cat <-
get_catalog( "piaac" ,
output_dir = file.path( path.expand( "~" ) , "PIAAC" ) )
# download the microdata to your local computer
piaac_cat <- lodown( "piaac" , piaac_cat )
Analysis Examples with the survey
library
Construct a multiply-imputed, complex sample survey design:
library(survey)
library(mitools)
piaac_design <- readRDS( file.path( path.expand( "~" ) , "PIAAC" , "prgusap1 design.rds" ) )
Variable Recoding
Add new columns to the data set:
piaac_design <-
update(
piaac_design ,
one = 1 ,
sex = factor( gender_r , labels = c( "male" , "female" ) ) ,
age_categories =
factor(
ageg10lfs ,
levels = 1:5 ,
labels = c( "24 or less" , "25-34" , "35-44" , "45-54" , "55 plus" )
) ,
working_at_paid_job_last_week = as.numeric( c_q01a == 1 )
)
Unweighted Counts
Count the unweighted number of records in the survey sample, overall and by groups:
MIcombine( with( piaac_design , svyby( ~ one , ~ one , unwtd.count ) ) )
MIcombine( with( piaac_design , svyby( ~ one , ~ age_categories , unwtd.count ) ) )
Weighted Counts
Count the weighted size of the generalizable population, overall and by groups:
MIcombine( with( piaac_design , svytotal( ~ one ) ) )
MIcombine( with( piaac_design ,
svyby( ~ one , ~ age_categories , svytotal )
) )
Descriptive Statistics
Calculate the mean (average) of a linear variable, overall and by groups:
MIcombine( with( piaac_design , svymean( ~ pvnum , na.rm = TRUE ) ) )
MIcombine( with( piaac_design ,
svyby( ~ pvnum , ~ age_categories , svymean , na.rm = TRUE )
) )
Calculate the distribution of a categorical variable, overall and by groups:
MIcombine( with( piaac_design , svymean( ~ sex ) ) )
MIcombine( with( piaac_design ,
svyby( ~ sex , ~ age_categories , svymean )
) )
Calculate the sum of a linear variable, overall and by groups:
MIcombine( with( piaac_design , svytotal( ~ pvnum , na.rm = TRUE ) ) )
MIcombine( with( piaac_design ,
svyby( ~ pvnum , ~ age_categories , svytotal , na.rm = TRUE )
) )
Calculate the weighted sum of a categorical variable, overall and by groups:
MIcombine( with( piaac_design , svytotal( ~ sex ) ) )
MIcombine( with( piaac_design ,
svyby( ~ sex , ~ age_categories , svytotal )
) )
Calculate the median (50th percentile) of a linear variable, overall and by groups:
MIcombine( with( piaac_design ,
svyquantile(
~ pvnum ,
0.5 , se = TRUE , na.rm = TRUE
) ) )
MIcombine( with( piaac_design ,
svyby(
~ pvnum , ~ age_categories , svyquantile ,
0.5 , se = TRUE ,
keep.var = TRUE , ci = TRUE , na.rm = TRUE
) ) )
Estimate a ratio:
MIcombine( with( piaac_design ,
svyratio( numerator = ~ pvnum , denominator = ~ pvlit , na.rm = TRUE )
) )
Subsetting
Restrict the survey design to self-reported fair or poor health:
sub_piaac_design <- subset( piaac_design , i_q08 %in% 4:5 )
Calculate the mean (average) of this subset:
MIcombine( with( sub_piaac_design , svymean( ~ pvnum , 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 <-
MIcombine( with( piaac_design ,
svymean( ~ pvnum , na.rm = TRUE )
) )
coef( this_result )
SE( this_result )
confint( this_result )
cv( this_result )
grouped_result <-
MIcombine( with( piaac_design ,
svyby( ~ pvnum , ~ age_categories , 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( piaac_design$designs[[1]] )
Calculate the complex sample survey-adjusted variance of any statistic:
MIcombine( with( piaac_design , svyvar( ~ pvnum , na.rm = TRUE ) ) )
Include the complex sample design effect in the result for a specific statistic:
# SRS without replacement
MIcombine( with( piaac_design ,
svymean( ~ pvnum , na.rm = TRUE , deff = TRUE )
) )
# SRS with replacement
MIcombine( with( piaac_design ,
svymean( ~ pvnum , 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:
MIsvyciprop( ~ working_at_paid_job_last_week , piaac_design ,
method = "likelihood" )
Regression Models and Tests of Association
Perform a design-based t-test:
MIsvyttest( pvnum ~ working_at_paid_job_last_week , piaac_design )
Perform a chi-squared test of association for survey data:
MIsvychisq( ~ working_at_paid_job_last_week + sex , piaac_design )
Perform a survey-weighted generalized linear model:
glm_result <-
MIcombine( with( piaac_design ,
svyglm( pvnum ~ working_at_paid_job_last_week + sex )
) )
summary( glm_result )
Replication Example
The OECD’s Technical Report Table 18.9 on PDF page 455 includes statistics and standard errors for the three PIAAC domains. This code precisely replicates the Austria row shown in that official table.
austria_design <-
readRDS( file.path( path.expand( "~" ) , "PIAAC" , "prgautp1 design.rds" ) )
austria_pvlit <-
MIcombine( with( austria_design , svymean( ~ pvlit , na.rm = TRUE ) ) )
austria_pvnum <-
MIcombine( with( austria_design , svymean( ~ pvnum , na.rm = TRUE ) ) )
austria_pvpsl <-
MIcombine( with( austria_design , svymean( ~ pvpsl , na.rm = TRUE ) ) )
# confirm each estimate and standard error matches the published statistics
stopifnot( round( coef( austria_pvlit ) ) == 269 )
stopifnot( round( SE( austria_pvlit ) , 1 ) == 0.7 )
stopifnot( round( coef( austria_pvnum ) ) == 275 )
stopifnot( round( SE( austria_pvnum ) , 1 ) == 0.9 )
stopifnot( round( coef( austria_pvpsl ) ) == 284 )
stopifnot( round( SE( austria_pvpsl ) , 1 ) == 0.7 )