Pesquisa Nacional de Saude (PNS)
Brazil’s health survey, measuring medical conditions, risk behaviors, access to and use of care.
One consolidated table with one row per individual within each sampled household.
A complex sample survey designed to generalize to Brazil’s civilian population.
Released at approximately five year intervals starting in 2013.
Administered by Instituto Brasileiro de Geografia e Estatistica partnered with the Ministério da Saúde.
Please skim before you begin:
A haiku regarding this microdata:
# cheer the ministry!
# with each caipirinha, or
# fail sex life module
Download, Import, Preparation
Download and import the dictionary file:
<- tempfile()
dictionary_tf
<-
dictionary_url "https://ftp.ibge.gov.br/PNS/2019/Microdados/Documentacao/Dicionario_e_input_20220530.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( '@00001' , 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 tabs, multiple spaces and spaces at the end of each string
<- gsub( "\t" , " " , sas_lines )
sas_lines <- 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 data file:
<- tempfile()
this_tf
<-
this_url "https://ftp.ibge.gov.br/PNS/2019/Microdados/Dados/PNS_2019_20220525.zip"
download.file( this_url , this_tf , mode = 'wb' )
Import the latest data file:
library(readr)
<-
pns_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( pns_tbl )
pns_df
names( pns_df ) <- tolower( names( pns_df ) )
'one' ] <- 1 pns_df[ ,
Save Locally
Save the object at any point:
# pns_fn <- file.path( path.expand( "~" ) , "PNS" , "this_file.rds" )
# saveRDS( pns_df , file = pns_fn , compress = FALSE )
Load the same object:
# pns_df <- readRDS( pns_fn )
Survey Design Definition
Construct a complex sample survey design:
library(survey)
options( survey.lonely.psu = "adjust" )
<-
pns_prestratified_design svydesign(
id = ~ upa_pns ,
strata = ~v0024 ,
data = subset( pns_df , !is.na( v0028 ) ) ,
weights = ~v0028 ,
nest = TRUE
)
<-
popc.types data.frame(
v00283 = as.character( unique( pns_df[ , 'v00283' ] ) ) ,
Freq = as.numeric( unique( pns_df[ , 'v00282' ] ) )
)
<- popc.types[ order( popc.types[ , 'v00283' ] ) , ]
popc.types
<-
pns_design postStratify(
pns_prestratified_design ,strata = ~v00283 ,
population = popc.types
)
Variable Recoding
Add new columns to the data set:
<-
pns_design update(
pns_design ,
medical_insurance = ifelse( i00102 %in% 1:2 , as.numeric( i00102 == 1 ) , NA ) ,
uf_name =
factor(
as.numeric( v0001 ) ,
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( c008 , seq( 5 , 90 , 5 ) ) ) ,
male = as.numeric( v006 == 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( pns_design , "sampling" ) != 0 )
svyby( ~ one , ~ uf_name , pns_design , unwtd.count )
Weighted Counts
Count the weighted size of the generalizable population, overall and by groups:
svytotal( ~ one , pns_design )
svyby( ~ one , ~ uf_name , pns_design , svytotal )
Descriptive Statistics
Calculate the mean (average) of a linear variable, overall and by groups:
svymean( ~ e01602 , pns_design , na.rm = TRUE )
svyby( ~ e01602 , ~ uf_name , pns_design , svymean , na.rm = TRUE )
Calculate the distribution of a categorical variable, overall and by groups:
svymean( ~ c006 , pns_design )
svyby( ~ c006 , ~ uf_name , pns_design , svymean )
Calculate the sum of a linear variable, overall and by groups:
svytotal( ~ e01602 , pns_design , na.rm = TRUE )
svyby( ~ e01602 , ~ uf_name , pns_design , svytotal , na.rm = TRUE )
Calculate the weighted sum of a categorical variable, overall and by groups:
svytotal( ~ c006 , pns_design )
svyby( ~ c006 , ~ uf_name , pns_design , svytotal )
Calculate the median (50th percentile) of a linear variable, overall and by groups:
svyquantile( ~ e01602 , pns_design , 0.5 , na.rm = TRUE )
svyby(
~ e01602 ,
~ uf_name ,
pns_design ,
svyquantile , 0.5 ,
ci = TRUE , na.rm = TRUE
)
Estimate a ratio:
svyratio(
numerator = ~ p00104 ,
denominator = ~ p00404 ,
pns_design ,na.rm = TRUE
)
Subsetting
Restrict the survey design to individuals that exercise three or more days per week:
<- subset( pns_design , p035 %in% 3:7 ) sub_pns_design
Calculate the mean (average) of this subset:
svymean( ~ e01602 , sub_pns_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( ~ e01602 , pns_design , na.rm = TRUE )
this_result
coef( this_result )
SE( this_result )
confint( this_result )
cv( this_result )
<-
grouped_result svyby(
~ e01602 ,
~ uf_name ,
pns_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( pns_design )
Calculate the complex sample survey-adjusted variance of any statistic:
svyvar( ~ e01602 , pns_design , na.rm = TRUE )
Include the complex sample design effect in the result for a specific statistic:
# SRS without replacement
svymean( ~ e01602 , pns_design , na.rm = TRUE , deff = TRUE )
# SRS with replacement
svymean( ~ e01602 , pns_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( ~ medical_insurance , pns_design ,
method = "likelihood" , na.rm = TRUE )
Regression Models and Tests of Association
Perform a design-based t-test:
svyttest( e01602 ~ medical_insurance , pns_design )
Perform a chi-squared test of association for survey data:
svychisq(
~ medical_insurance + c006 ,
pns_design )
Perform a survey-weighted generalized linear model:
<-
glm_result svyglm(
~ medical_insurance + c006 ,
e01602
pns_design
)
summary( glm_result )
Replication Example
This example matches Estimando totais
of gross monthly income from the official PNSIBGE
R package:
<- svytotal( ~ e01602 , pns_design , na.rm = TRUE )
total_renda stopifnot( round( coef( total_renda ) , 0 ) == 213227874692 )
stopifnot( round( SE( total_renda ) , 0 ) == 3604489769 )
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 PNS users, this code replicates previously-presented examples:
library(srvyr)
<- as_survey( pns_design ) pns_srvyr_design
Calculate the mean (average) of a linear variable, overall and by groups:
%>%
pns_srvyr_design summarize( mean = survey_mean( e01602 , na.rm = TRUE ) )
%>%
pns_srvyr_design group_by( uf_name ) %>%
summarize( mean = survey_mean( e01602 , na.rm = TRUE ) )