National Survey of OAA Participants (NPS)

Build Status Build status

The National Survey of OAA Participants measures program satisfaction with state agency community services for American seniors.

  • One table with one row per sampled senior respondent.

  • A complex sample survey designed to generalize to non-institutionalized beneficiaries of Area Agencies on Aging (AAA) within the United States.

  • Released annually since 2003.

  • Administered by the U.S. Administration on Aging.

Simplified Download and Importation

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

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

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

Analysis Examples with the survey library

Construct a complex sample survey design:

library(survey)

nps_df <- 
    readRDS( 
        file.path( path.expand( "~" ) , "NPS" , 
            "2015 transportation.rds" ) )

nps_design <- 
    svrepdesign( 
        data = nps_df , 
        repweights = "pstotwgt[0-9]" , 
        weights = ~ pstotwgt , 
        type = "Fay" , 
        rho = 0.29986 , 
        mse = TRUE
    )

Variable Recoding

Add new columns to the data set:

nps_design <- 
    update( 
        nps_design , 
        
        age_category =
            factor( agec , levels = 2:5 , labels =
            c( "60-64" , "65-74" , "75-84" , "85+" ) ) ,
        
        gender = factor( gender , labels = c( "male" , "female" ) ) ,
        
        trip_this_week = as.numeric( trdays %in% 1:2 )

    )

Unweighted Counts

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

sum( weights( nps_design , "sampling" ) != 0 )

svyby( ~ one , ~ age_category , nps_design , unwtd.count )

Weighted Counts

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

svytotal( ~ one , nps_design )

svyby( ~ one , ~ age_category , nps_design , svytotal )

Descriptive Statistics

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

svymean( ~ adlaoa6p , nps_design , na.rm = TRUE )

svyby( ~ adlaoa6p , ~ age_category , nps_design , svymean , na.rm = TRUE )

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

svymean( ~ gender , nps_design )

svyby( ~ gender , ~ age_category , nps_design , svymean )

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

svytotal( ~ adlaoa6p , nps_design , na.rm = TRUE )

svyby( ~ adlaoa6p , ~ age_category , nps_design , svytotal , na.rm = TRUE )

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

svytotal( ~ gender , nps_design )

svyby( ~ gender , ~ age_category , nps_design , svytotal )

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

svyquantile( ~ adlaoa6p , nps_design , 0.5 , na.rm = TRUE )

svyby( 
    ~ adlaoa6p , 
    ~ age_category , 
    nps_design , 
    svyquantile , 
    0.5 ,
    ci = TRUE ,
    keep.var = TRUE ,
    na.rm = TRUE
)

Estimate a ratio:

svyratio( 
    numerator = ~ adlaoa6p , 
    denominator = ~ iadlaoa7 , 
    nps_design ,
    na.rm = TRUE
)

Subsetting

Restrict the survey design to beneficiaries who live alone:

sub_nps_design <- subset( nps_design , livealone == 1 )

Calculate the mean (average) of this subset:

svymean( ~ adlaoa6p , sub_nps_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( ~ adlaoa6p , nps_design , na.rm = TRUE )

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

grouped_result <-
    svyby( 
        ~ adlaoa6p , 
        ~ age_category , 
        nps_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( nps_design )

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

svyvar( ~ adlaoa6p , nps_design , na.rm = TRUE )

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

# SRS without replacement
svymean( ~ adlaoa6p , nps_design , na.rm = TRUE , deff = TRUE )

# SRS with replacement
svymean( ~ adlaoa6p , nps_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( ~ trip_this_week , nps_design ,
    method = "likelihood" )

Regression Models and Tests of Association

Perform a design-based t-test:

svyttest( adlaoa6p ~ trip_this_week , nps_design )

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

svychisq( 
    ~ trip_this_week + gender , 
    nps_design 
)

Perform a survey-weighted generalized linear model:

glm_result <- 
    svyglm( 
        adlaoa6p ~ trip_this_week + gender , 
        nps_design 
    )

summary( glm_result )

0.39 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 NPS users, this code replicates previously-presented examples:

library(srvyr)
nps_srvyr_design <- as_survey( nps_design )

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

nps_srvyr_design %>%
    summarize( mean = survey_mean( adlaoa6p , na.rm = TRUE ) )

nps_srvyr_design %>%
    group_by( age_category ) %>%
    summarize( mean = survey_mean( adlaoa6p , na.rm = TRUE ) )

Replication Example