Trends in International Mathematics and Science Study (TIMSS)

The Trends in International Mathematics and Science Study (TIMSS) tracks the math and science competency of fourth graders across about fifty nations.

• A series of tables with one record per school (ACG), per student (ASG), per teacher (ATG), as well as files containing student achievement (ASA), home background (ASH), student-teacher linkage (AST), and within-country scoring reliability (ASR).

• A complex sample survey designed to generalize to the fourth-grade student population of participating countries.

• Released quadrennially since 1995.

• Funded by the International Association for the Evaluation of Educational Achievement and compiled by the Lynch School of Education at Boston College.

Simplified Download and Importation

The R lodown package easily downloads and imports all available TIMSS microdata by simply specifying "timss" 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( "timss" , output_dir = file.path( path.expand( "~" ) , "TIMSS" ) )

lodown also provides a catalog of available microdata extracts with the get_catalog() function. After requesting the TIMSS 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 TIMSS microdata files
timss_cat <-
    get_catalog( "timss" ,
        output_dir = file.path( path.expand( "~" ) , "TIMSS" ) )

# 2015 only
timss_cat <- subset( timss_cat , year == 2015 )
# download the microdata to your local computer
timss_cat <- lodown( "timss" , timss_cat )

Analysis Examples with the survey library  

Construct a multiply-imputed, complex sample survey design:

library(survey)
library(mitools)
library(RSQLite)

# load the ASG (student background) + ASH (home background) merged design
timss_design <- readRDS( file.path( path.expand( "~" ) , "TIMSS" , "2015/asg_design.rds" ) )

design_weights <- readRDS( file.path( path.expand( "~" ) , "TIMSS" , "2015/asg_weights.rds" ) )

five_tablenames <- paste0( "asg_2015_" , 1:5 )

timss_design <- lodown:::svyMDBdesign( timss_design )

Variable Recoding

Add new columns to the data set:

timss_design <- 
    update( 
        timss_design , 
        
        one = 1 ,
        
        idcntry = factor( idcntry ) ,
        
        sex = factor( itsex , labels = c( "male" , "female" ) ) ,
        
        born_2005_or_later = as.numeric( itbirthy >= 2005 )

    )

Unweighted Counts

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

MIcombine( with( timss_design , svyby( ~ one , ~ one , unwtd.count ) ) )

MIcombine( with( timss_design , svyby( ~ one , ~ sex , unwtd.count ) ) )

Weighted Counts

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

MIcombine( with( timss_design , svytotal( ~ one ) ) )

MIcombine( with( timss_design ,
    svyby( ~ one , ~ sex , svytotal )
) )

Descriptive Statistics

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

MIcombine( with( timss_design , svymean( ~ asmmat ) ) )

MIcombine( with( timss_design ,
    svyby( ~ asmmat , ~ sex , svymean )
) )

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

MIcombine( with( timss_design , svymean( ~ idcntry ) ) )

MIcombine( with( timss_design ,
    svyby( ~ idcntry , ~ sex , svymean )
) )

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

MIcombine( with( timss_design , svytotal( ~ asmmat ) ) )

MIcombine( with( timss_design ,
    svyby( ~ asmmat , ~ sex , svytotal )
) )

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

MIcombine( with( timss_design , svytotal( ~ idcntry ) ) )

MIcombine( with( timss_design ,
    svyby( ~ idcntry , ~ sex , svytotal )
) )

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

MIcombine( with( timss_design ,
    svyquantile(
        ~ asmmat ,
        0.5 , se = TRUE 
) ) )

MIcombine( with( timss_design ,
    svyby(
        ~ asmmat , ~ sex , svyquantile ,
        0.5 , se = TRUE ,
        keep.var = TRUE , ci = TRUE 
) ) )

Estimate a ratio:

MIcombine( with( timss_design ,
    svyratio( numerator = ~ asssci , denominator = ~ asmmat )
) )

Subsetting

Restrict the survey design to Australia, Austria, Azerbaijan, Belgium (French):

sub_timss_design <- subset( timss_design , idcntry %in% c( 36 , 40 , 31 , 957 ) )

Calculate the mean (average) of this subset:

MIcombine( with( sub_timss_design , svymean( ~ asmmat ) ) )

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( timss_design ,
        svymean( ~ asmmat )
    ) )

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

grouped_result <-
    MIcombine( with( timss_design ,
        svyby( ~ asmmat , ~ sex , svymean )
    ) )

coef( grouped_result )
SE( grouped_result )
confint( grouped_result )
cv( grouped_result )

Calculate the degrees of freedom of any survey design object:

degf( timss_design$designs[[1]] )

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

MIcombine( with( timss_design , svyvar( ~ asmmat ) ) )

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

# SRS without replacement
MIcombine( with( timss_design ,
    svymean( ~ asmmat , deff = TRUE )
) )

# SRS with replacement
MIcombine( with( timss_design ,
    svymean( ~ asmmat , deff = "replace" )
) )

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

MIsvyciprop( ~ born_2001_or_later , timss_design ,
    method = "likelihood" , na.rm = TRUE )

Regression Models and Tests of Association

Perform a design-based t-test:

MIsvyttest( asmmat ~ born_2001_or_later , timss_design )

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

MIsvychisq( ~ born_2001_or_later + idcntry , timss_design )

Perform a survey-weighted generalized linear model:

glm_result <- 
    MIcombine( with( timss_design ,
        svyglm( asmmat ~ born_2001_or_later + idcntry )
    ) )
    
summary( glm_result )

---

Replication Example