Pesquisa Nacional por Amostra de Domicilios (PNAD)
Brazil’s principal labor force survey, measuring education, employment, income, housing characteristics.
One consolidated table with one row per individual within each sampled household.
A complex sample survey designed to generalize to the civilian non-institutional population of Brazil.
Released quarterly since 2012, with microdata available both quarterly and annually.
Administered by the Instituto Brasileiro de Geografia e Estatistica.
Please skim before you begin:
This human-composed haiku or a bouquet of artificial intelligence-generated limericks
# mineiro data
# love verdade gave to me
# twelve karaoke..
Download, Import, Preparation
Download and import the dictionary file:
<- tempfile()
dictionary_tf
<-
dictionary_url paste0(
"https://ftp.ibge.gov.br/Trabalho_e_Rendimento/" ,
"Pesquisa_Nacional_por_Amostra_de_Domicilios_continua/" ,
"Trimestral/Microdados/Documentacao/Dicionario_e_input_20221031.zip"
)
download.file( dictionary_url , dictionary_tf , mode = 'wb' )
<- unzip( dictionary_tf , exdir = tempdir() )
dictionary_files
<- grep( '\\.sas$' , dictionary_files , value = TRUE )
sas_fn
<- readLines( sas_fn , encoding = 'latin1' ) sas_lines
Determine fixed-width file positions from the SAS import script:
<- grep( '@0001' , sas_lines )
sas_start
<- grep( ';' , sas_lines )
sas_end
<- sas_end[ sas_end > sas_start ][ 1 ]
sas_end
<- sas_lines[ seq( sas_start , sas_end - 1 ) ]
sas_lines
# remove SAS comments
<- gsub( "\\/\\*(.*)" , "" , sas_lines )
sas_lines
# remove multiple spaces and spaces at the end of each string
<- gsub( "( +)" , " " , sas_lines )
sas_lines <- gsub( " $" , "" , sas_lines )
sas_lines
<-
sas_df read.table(
textConnection( sas_lines ) ,
sep = ' ' ,
col.names = c( 'position' , 'column_name' , 'length' ) ,
header = FALSE
)
'character' ] <- grepl( '\\$' , sas_df[ , 'length' ] )
sas_df[ ,
'position' ] <- as.integer( gsub( "\\@" , "" , sas_df[ , 'position' ] ) )
sas_df[ ,
'length' ] <- as.integer( gsub( "\\$" , "" , sas_df[ , 'length' ] ) )
sas_df[ ,
stopifnot(
sum( sas_df[ , 'length' ] ) ==
nrow( sas_df ) , 'position' ] + sas_df[ nrow( sas_df ) , 'length' ] - 1 )
( sas_df[ )
Download the latest quarterly file:
<- tempfile()
this_tf
<-
this_url paste0(
"https://ftp.ibge.gov.br/Trabalho_e_Rendimento/" ,
"Pesquisa_Nacional_por_Amostra_de_Domicilios_continua/" ,
"Trimestral/Microdados/2023/PNADC_012023.zip"
)
download.file( this_url , this_tf , mode = 'wb' )
Import the latest quarterly file:
library(readr)
<-
pnad_tbl read_fwf(
this_tf ,fwf_widths(
widths = sas_df[ , 'length' ] ,
col_names = sas_df[ , 'column_name' ]
) ,col_types =
paste0( ifelse( sas_df[ , 'character' ] , "c" , "d" ) , collapse = '' )
)
<- data.frame( pnad_tbl )
pnad_df
names( pnad_df ) <- tolower( names( pnad_df ) )
'one' ] <- 1 pnad_df[ ,
Save locally
Save the object at any point:
# pnad_fn <- file.path( path.expand( "~" ) , "PNAD" , "this_file.rds" )
# saveRDS( pnad_df , file = pnad_fn , compress = FALSE )
Load the same object:
# pnad_df <- readRDS( pnad_fn )
Survey Design Definition
Construct a complex sample survey design:
library(survey)
<-
pnad_design svrepdesign(
data = pnad_df ,
weight = ~ v1028 ,
type = 'bootstrap' ,
repweights = 'v1028[0-9]+' ,
mse = TRUE ,
)
Variable Recoding
Add new columns to the data set:
<-
pnad_design update(
pnad_design ,
pia = as.numeric( v2009 >= 14 )
)
<-
pnad_design update(
pnad_design ,
ocup_c = ifelse( pia == 1 , as.numeric( vd4002 %in% 1 ) , NA ) ,
desocup30 = ifelse( pia == 1 , as.numeric( vd4002 %in% 2 ) , NA )
)
<-
pnad_design
update(
pnad_design ,
uf_name =
factor(
as.numeric( uf ) ,
levels =
c(11L, 12L, 13L, 14L, 15L, 16L, 17L, 21L, 22L, 23L, 24L, 25L,
26L, 27L, 28L, 29L, 31L, 32L, 33L, 35L, 41L, 42L, 43L, 50L, 51L,
52L, 53L) ,
labels =
c("Rondonia", "Acre", "Amazonas", "Roraima", "Para", "Amapa",
"Tocantins", "Maranhao", "Piaui", "Ceara", "Rio Grande do Norte",
"Paraiba", "Pernambuco", "Alagoas", "Sergipe", "Bahia", "Minas Gerais",
"Espirito Santo", "Rio de Janeiro", "Sao Paulo", "Parana", "Santa Catarina",
"Rio Grande do Sul", "Mato Grosso do Sul", "Mato Grosso", "Goias",
"Distrito Federal")
) ,
age_categories = factor( 1 + findInterval( v2009 , seq( 5 , 60 , 5 ) ) ) ,
male = as.numeric( v2007 == 1 ) ,
region = substr( uf , 1 , 1 ) ,
# calculate usual income from main job
# (rendimento habitual do trabalho principal)
vd4016n = ifelse( pia %in% 1 & vd4015 %in% 1 , vd4016 , NA ) ,
# calculate effective income from main job
# (rendimento efetivo do trabalho principal)
vd4017n = ifelse( pia %in% 1 & vd4015 %in% 1 , vd4017 , NA ) ,
# calculate usual income from all jobs
# (variavel rendimento habitual de todos os trabalhos)
vd4019n = ifelse( pia %in% 1 & vd4015 %in% 1 , vd4019 , NA ) ,
# calculate effective income from all jobs
# (rendimento efetivo do todos os trabalhos)
vd4020n = ifelse( pia %in% 1 & vd4015 %in% 1 , vd4020 , NA ) ,
# determine the potential labor force
pea_c = as.numeric( ocup_c == 1 | desocup30 == 1 )
)
Analysis Examples with the survey
library
Unweighted Counts
Count the unweighted number of records in the survey sample, overall and by groups:
sum( weights( pnad_design , "sampling" ) != 0 )
svyby( ~ one , ~ uf_name , pnad_design , unwtd.count )
Weighted Counts
Count the weighted size of the generalizable population, overall and by groups:
svytotal( ~ one , pnad_design )
svyby( ~ one , ~ uf_name , pnad_design , svytotal )
Descriptive Statistics
Calculate the mean (average) of a linear variable, overall and by groups:
svymean( ~ vd4020n , pnad_design , na.rm = TRUE )
svyby( ~ vd4020n , ~ uf_name , pnad_design , svymean , na.rm = TRUE )
Calculate the distribution of a categorical variable, overall and by groups:
svymean( ~ age_categories , pnad_design )
svyby( ~ age_categories , ~ uf_name , pnad_design , svymean )
Calculate the sum of a linear variable, overall and by groups:
svytotal( ~ vd4020n , pnad_design , na.rm = TRUE )
svyby( ~ vd4020n , ~ uf_name , pnad_design , svytotal , na.rm = TRUE )
Calculate the weighted sum of a categorical variable, overall and by groups:
svytotal( ~ age_categories , pnad_design )
svyby( ~ age_categories , ~ uf_name , pnad_design , svytotal )
Calculate the median (50th percentile) of a linear variable, overall and by groups:
svyquantile( ~ vd4020n , pnad_design , 0.5 , na.rm = TRUE )
svyby(
~ vd4020n ,
~ uf_name ,
pnad_design ,
svyquantile , 0.5 ,
ci = TRUE , na.rm = TRUE
)
Estimate a ratio:
svyratio(
numerator = ~ ocup_c ,
denominator = ~ pea_c ,
pnad_design ,na.rm = TRUE
)
Subsetting
Restrict the survey design to employed persons:
<- subset( pnad_design , ocup_c == 1 ) sub_pnad_design
Calculate the mean (average) of this subset:
svymean( ~ vd4020n , sub_pnad_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:
<- svymean( ~ vd4020n , pnad_design , na.rm = TRUE )
this_result
coef( this_result )
SE( this_result )
confint( this_result )
cv( this_result )
<-
grouped_result svyby(
~ vd4020n ,
~ uf_name ,
pnad_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( pnad_design )
Calculate the complex sample survey-adjusted variance of any statistic:
svyvar( ~ vd4020n , pnad_design , na.rm = TRUE )
Include the complex sample design effect in the result for a specific statistic:
# SRS without replacement
svymean( ~ vd4020n , pnad_design , na.rm = TRUE , deff = TRUE )
# SRS with replacement
svymean( ~ vd4020n , pnad_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( ~ male , pnad_design ,
method = "likelihood" )
Regression Models and Tests of Association
Perform a design-based t-test:
svyttest( vd4020n ~ male , pnad_design )
Perform a chi-squared test of association for survey data:
svychisq(
~ male + age_categories ,
pnad_design )
Perform a survey-weighted generalized linear model:
<-
glm_result svyglm(
~ male + age_categories ,
vd4020n
pnad_design
)
summary( glm_result )
Replication Example
This example matches statistics and coefficients of variation from Tabela 4092 - Pessoas de 14 anos ou mais de idade, por condição em relação à força de trabalho e condição de ocupação:
<- svytotal( ~ pia , pnad_design , na.rm = TRUE )
nationwide_adult_population
stopifnot( round( coef( nationwide_adult_population ) / 1000000 , 3 ) == 174.228 )
stopifnot( round( cv( nationwide_adult_population ) / 1000000 , 3 ) == 0 )
<- svytotal( ~ pea_c , pnad_design , na.rm = TRUE )
nationwide_labor_force
stopifnot( round( coef( nationwide_labor_force ) / 1000000 , 3 ) == 107.257 )
stopifnot( round( cv( nationwide_labor_force ) * 100 , 1 ) == 0.2 )
<- svytotal( ~ ocup_c , pnad_design , na.rm = TRUE )
nationwide_employed
stopifnot( round( coef( nationwide_employed ) / 1000000 , 3 ) == 97.825 )
stopifnot( round( cv( nationwide_employed ) * 100 , 1 ) == 0.2 )
<- svytotal( ~ desocup30 , pnad_design , na.rm = TRUE )
nationwide_unemployed
stopifnot( round( coef( nationwide_unemployed ) / 1000000 , 3 ) == 9.432 )
stopifnot( round( cv( nationwide_unemployed ) * 100 , 1 ) == 1.2 )
<-
nationwide_not_in_labor_force svytotal( ~ as.numeric( pia & !pea_c ) , pnad_design , na.rm = TRUE )
stopifnot( round( coef( nationwide_not_in_labor_force ) / 1000000 , 3 ) == 66.972 )
stopifnot( round( cv( nationwide_not_in_labor_force ) * 100 , 1 ) == 0.3 )
Poverty and Inequality Estimation with convey
The R convey
library estimates measures of income concentration, poverty, inequality, and wellbeing. This textbook details the available features. As a starting point for PNAD users, this code calculates the gini coefficient on complex sample survey data:
library(convey)
<- convey_prep( pnad_design )
pnad_design
svygini( ~ vd4020n , pnad_design , na.rm = TRUE )
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 PNAD users, this code replicates previously-presented examples:
library(srvyr)
<- as_survey( pnad_design ) pnad_srvyr_design
Calculate the mean (average) of a linear variable, overall and by groups:
%>%
pnad_srvyr_design summarize( mean = survey_mean( vd4020n , na.rm = TRUE ) )
%>%
pnad_srvyr_design group_by( uf_name ) %>%
summarize( mean = survey_mean( vd4020n , na.rm = TRUE ) )