Consumer Expenditure Survey (CES)
The Consumer Expenditure Survey (CES) is the authoritative data source to understand how Americans spend money. Participating households keep a running diary about every purchase over fifteen months. Those diaries are then summed up into precise expenditure categories.
One table of survey responses per quarter with one row per sampled household (consumer unit). Additional tables containing one record per expenditure
A complex sample survey designed to generalize to the civilian non-institutional population of the United States.
Released annually since 1996.
Administered by the Bureau of Labor Statistics.
Simplified Download and Importation
The R lodown package easily downloads and imports all available CES microdata by simply specifying "ces" 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( "ces" , output_dir = file.path( path.expand( "~" ) , "CES" ) )lodown also provides a catalog of available microdata extracts with the get_catalog() function. After requesting the CES 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 CES microdata files
ces_cat <-
get_catalog( "ces" ,
output_dir = file.path( path.expand( "~" ) , "CES" ) )
# 2016 only
ces_cat <- subset( ces_cat , year == 2016 )
# download the microdata to your local computer
ces_cat <- lodown( "ces" , ces_cat )Analysis Examples with the survey library
Construct a multiply-imputed, complex sample survey design:
library(survey)
library(mitools)
# read in the five quarters of family data files (fmli)
fmli161x <- readRDS( file.path( path.expand( "~" ) , "CES" , "2016/fmli161x.rds" ) )
fmli162 <- readRDS( file.path( path.expand( "~" ) , "CES" , "2016/fmli162.rds" ) )
fmli163 <- readRDS( file.path( path.expand( "~" ) , "CES" , "2016/fmli163.rds" ) )
fmli164 <- readRDS( file.path( path.expand( "~" ) , "CES" , "2016/fmli164.rds" ) )
fmli171 <- readRDS( file.path( path.expand( "~" ) , "CES" , "2016/fmli171.rds" ) )
fmli161x$qtr <- 1
fmli162$qtr <- 2
fmli163$qtr <- 3
fmli164$qtr <- 4
fmli171$qtr <- 5
fmli171 <- fmli171[ , names( fmli161x ) ]
fmly <- rbind( fmli161x , fmli162 , fmli163 , fmli164 , fmli171 )
rm( fmli161x , fmli162 , fmli163 , fmli164 , fmli171 )
wtrep <- c( paste0( "wtrep" , stringr::str_pad( 1:44 , 2 , pad = "0" ) ) , "finlwt21" )
for ( i in wtrep ) fmly[ is.na( fmly[ , i ] ) , i ] <- 0
# create a new variable in the fmly data table called 'totalexp'
# that contains the sum of the total expenditure from the current and previous quarters
fmly$totalexp <- rowSums( fmly[ , c( "totexppq" , "totexpcq" ) ] , na.rm = TRUE )
# immediately convert missing values (NA) to zeroes
fmly[ is.na( fmly$totalexp ) , "totalexp" ] <- 0
# annualize the total expenditure by multiplying the total expenditure by four,
# creating a new variable 'annexp' in the fmly data table
fmly <- transform( fmly , annexp = totalexp * 4 )
# add a column of ones
fmly$one <- 1
# create a vector containing all of the multiply-imputed variables
# (leaving the numbers off the end)
mi_vars <- gsub( "5$" , "" , grep( "[a-z]5$" , names( fmly ) , value = TRUE ) )
# loop through each of the five variables..
for ( i in 1:5 ){
# copy the 'fmly' table over to a new temporary data frame 'x'
x <- fmly
# loop through each of the multiply-imputed variables..
for ( j in mi_vars ){
# copy the contents of the current column (for example 'welfare1')
# over to a new column ending in 'mi' (for example 'welfaremi')
x[ , paste0( j , 'mi' ) ] <- x[ , paste0( j , i ) ]
# delete the all five of the imputed variable columns
x <- x[ , !( names( x ) %in% paste0( j , 1:5 ) ) ]
}
# save the current table in the sqlite database as 'imp1' 'imp2' etc.
assign( paste0( 'imp' , i ) , x )
# remove the temporary table
rm( x )
}
# containing the five multiply-imputed data tables - imp1 through imp5
ces_design <-
svrepdesign(
weights = ~finlwt21 ,
repweights = "wtrep[0-9]+" ,
data = imputationList( list( imp1 , imp2 , imp3 , imp4 , imp5 ) ) ,
type = "BRR" ,
combined.weights = TRUE ,
mse = TRUE
)
rm( imp1 , imp2 , imp3 , imp4 , imp5 )Variable Recoding
Add new columns to the data set:
ces_design <-
update(
ces_design ,
any_food_stamp = as.numeric( jfs_amtmi > 0 )
)Unweighted Counts
Count the unweighted number of records in the survey sample, overall and by groups:
MIcombine( with( ces_design , svyby( ~ one , ~ one , unwtd.count ) ) )
MIcombine( with( ces_design , svyby( ~ one , ~ bls_urbn , unwtd.count ) ) )Weighted Counts
Count the weighted size of the generalizable population, overall and by groups:
MIcombine( with( ces_design , svytotal( ~ one ) ) )
MIcombine( with( ces_design ,
svyby( ~ one , ~ bls_urbn , svytotal )
) )Descriptive Statistics
Calculate the mean (average) of a linear variable, overall and by groups:
MIcombine( with( ces_design , svymean( ~ annexp ) ) )
MIcombine( with( ces_design ,
svyby( ~ annexp , ~ bls_urbn , svymean )
) )Calculate the distribution of a categorical variable, overall and by groups:
MIcombine( with( ces_design , svymean( ~ sex_ref ) ) )
MIcombine( with( ces_design ,
svyby( ~ sex_ref , ~ bls_urbn , svymean )
) )Calculate the sum of a linear variable, overall and by groups:
MIcombine( with( ces_design , svytotal( ~ annexp ) ) )
MIcombine( with( ces_design ,
svyby( ~ annexp , ~ bls_urbn , svytotal )
) )Calculate the weighted sum of a categorical variable, overall and by groups:
MIcombine( with( ces_design , svytotal( ~ sex_ref ) ) )
MIcombine( with( ces_design ,
svyby( ~ sex_ref , ~ bls_urbn , svytotal )
) )Calculate the median (50th percentile) of a linear variable, overall and by groups:
MIcombine( with( ces_design ,
svyquantile(
~ annexp ,
0.5 , se = TRUE
) ) )
MIcombine( with( ces_design ,
svyby(
~ annexp , ~ bls_urbn , svyquantile ,
0.5 , se = TRUE ,
keep.var = TRUE , ci = TRUE
) ) )Estimate a ratio:
MIcombine( with( ces_design ,
svyratio( numerator = ~ annexp , denominator = ~ fincbtxmi )
) )Subsetting
Restrict the survey design to california residents:
sub_ces_design <- subset( ces_design , state == '06' )Calculate the mean (average) of this subset:
MIcombine( with( sub_ces_design , svymean( ~ annexp ) ) )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( ces_design ,
svymean( ~ annexp )
) )
coef( this_result )
SE( this_result )
confint( this_result )
cv( this_result )
grouped_result <-
MIcombine( with( ces_design ,
svyby( ~ annexp , ~ bls_urbn , svymean )
) )
coef( grouped_result )
SE( grouped_result )
confint( grouped_result )
cv( grouped_result )Calculate the degrees of freedom of any survey design object:
degf( ces_design$designs[[1]] )Calculate the complex sample survey-adjusted variance of any statistic:
MIcombine( with( ces_design , svyvar( ~ annexp ) ) )Include the complex sample design effect in the result for a specific statistic:
# SRS without replacement
MIcombine( with( ces_design ,
svymean( ~ annexp , deff = TRUE )
) )
# SRS with replacement
MIcombine( with( ces_design ,
svymean( ~ annexp , deff = "replace" )
) )Compute confidence intervals for proportions using methods that may be more accurate near 0 and 1. See ?svyciprop for alternatives:
MIsvyciprop( ~ any_food_stamp , ces_design ,
method = "likelihood" )Regression Models and Tests of Association
Perform a design-based t-test:
MIsvyttest( annexp ~ any_food_stamp , ces_design )Perform a chi-squared test of association for survey data:
MIsvychisq( ~ any_food_stamp + sex_ref , ces_design )Perform a survey-weighted generalized linear model:
glm_result <-
MIcombine( with( ces_design ,
svyglm( annexp ~ any_food_stamp + sex_ref )
) )
summary( glm_result )