Pesquisa Nacional de Saude (PNS)
Contributed by Dr. Djalma Pessoa <pessoad@gmail.com>
The Pesquisa Nacional de Saude (PNS) is Brazil’s healthcare survey.
One table with one row per long-questionnaire respondent and a second table with one row for all respondents.
A complex sample survey designed to generalize to Brazil’s civilian population.
First released 2013.
Administered by the Instituto Brasileiro de Geografia e Estatistica.
Simplified Download and Importation
The R lodown package easily downloads and imports all available PNS microdata by simply specifying "pns" 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( "pns" , output_dir = file.path( path.expand( "~" ) , "PNS" ) )lodown also provides a catalog of available microdata extracts with the get_catalog() function. After requesting the PNS 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 PNS microdata files
pns_cat <-
get_catalog( "pns" ,
output_dir = file.path( path.expand( "~" ) , "PNS" ) )
# download the microdata to your local computer
pns_cat <- lodown( "pns" , pns_cat )Analysis Examples with the survey library
Construct a complex sample survey design:
options( survey.lonely.psu = "adjust" )
library(survey)
pns_design <-
readRDS(
file.path(
path.expand( "~" ) , "PNS" ,
"2013 long questionnaire survey design.rds" )
)Variable Recoding
Add new columns to the data set:
pns_design <-
update(
pns_design ,
one = 1 ,
health_insurance = as.numeric( i001 == 1 )
)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 , 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 , pns_design , svytotal )Descriptive Statistics
Calculate the mean (average) of a linear variable, overall and by groups:
svymean( ~ w00101 , pns_design , na.rm = TRUE )
svyby( ~ w00101 , ~ uf , pns_design , svymean , na.rm = TRUE )Calculate the distribution of a categorical variable, overall and by groups:
svymean( ~ c006 , pns_design )
svyby( ~ c006 , ~ uf , pns_design , svymean )Calculate the sum of a linear variable, overall and by groups:
svytotal( ~ w00101 , pns_design , na.rm = TRUE )
svyby( ~ w00101 , ~ uf , 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 , pns_design , svytotal )Calculate the median (50th percentile) of a linear variable, overall and by groups:
svyquantile( ~ w00101 , pns_design , 0.5 , na.rm = TRUE )
svyby(
~ w00101 ,
~ uf ,
pns_design ,
svyquantile ,
0.5 ,
ci = TRUE ,
keep.var = TRUE ,
na.rm = TRUE
)Estimate a ratio:
svyratio(
numerator = ~ w00203 ,
denominator = ~ w00101 ,
pns_design ,
na.rm = TRUE
)Subsetting
Restrict the survey design to at least 30 minutes of physical activity:
sub_pns_design <- subset( pns_design , atfi04 == 1 )Calculate the mean (average) of this subset:
svymean( ~ w00101 , 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:
this_result <- svymean( ~ w00101 , pns_design , na.rm = TRUE )
coef( this_result )
SE( this_result )
confint( this_result )
cv( this_result )
grouped_result <-
svyby(
~ w00101 ,
~ uf ,
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( ~ w00101 , pns_design , na.rm = TRUE )Include the complex sample design effect in the result for a specific statistic:
# SRS without replacement
svymean( ~ w00101 , pns_design , na.rm = TRUE , deff = TRUE )
# SRS with replacement
svymean( ~ w00101 , 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( ~ health_insurance , pns_design ,
method = "likelihood" , na.rm = TRUE )Regression Models and Tests of Association
Perform a design-based t-test:
svyttest( w00101 ~ health_insurance , pns_design )Perform a chi-squared test of association for survey data:
svychisq(
~ health_insurance + c006 ,
pns_design
)Perform a survey-weighted generalized linear model:
glm_result <-
svyglm(
w00101 ~ health_insurance + c006 ,
pns_design
)
summary( glm_result )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)
pns_srvyr_design <- as_survey( pns_design )Calculate the mean (average) of a linear variable, overall and by groups:
pns_srvyr_design %>%
summarize( mean = survey_mean( w00101 , na.rm = TRUE ) )
pns_srvyr_design %>%
group_by( uf ) %>%
summarize( mean = survey_mean( w00101 , na.rm = TRUE ) )