Youth Risk Behavior Surveillance System (YRBSS)

The high school edition of the Behavioral Risk Factor Surveillance System (BRFSS).

One table with one row per sampled youth respondent.
A complex sample survey designed to generalize to all public and private school students in grades 9-12 in the United States.
Released biennially since 1993.
Administered by the Centers for Disease Control and Prevention.

Please skim before you begin:

Methodology of the Youth Risk Behavior Surveillance System
Wikipedia Entry
A haiku regarding this microdata:

# maladolescence
# epidemiology
# sex, drugs, rock and roll

Download, Import, Preparation

Load the SAScii library to interpret a SAS input program, and also re-arrange the SAS input program:

library(SAScii)

sas_url <-
    "https://www.cdc.gov/yrbs/files/2023/2023XXH_SAS_Input_Program.sas"

sas_text <- tolower( readLines( sas_url ) )

# find the (out of numerical order)
# `site` location variable's position
# within the SAS input program
site_location <- which( sas_text == '@1 site $3.' )

# find the start field's position
# within the SAS input program
input_location <- which( sas_text == "input" )

# create a vector from 1 to the length of the text file
sas_length <- seq( length( sas_text ) )

# remove the site_location
sas_length <- sas_length[ -site_location ]

# re-insert the site variable's location
# immediately after the starting position
sas_reorder <- 
    c( 
        sas_length[ seq( input_location ) ] , 
        site_location , 
        sas_length[ seq( input_location + 1 , length( sas_length ) ) ] 
    )

# re-order the sas text file
sas_text <- sas_text[ sas_reorder ]

sas_tf <- tempfile()

writeLines( sas_text , sas_tf )

Download and import the national file:

dat_tf <- tempfile()

dat_url <-
    "https://www.cdc.gov/yrbs/files/2023/XXH2023_YRBS_Data.dat"
    
download.file( dat_url , dat_tf , mode = 'wb' )

yrbss_df <- read.SAScii( dat_tf , sas_tf )

names( yrbss_df ) <- tolower( names( yrbss_df ) )

yrbss_df[ , 'one' ] <- 1

Save Locally

Save the object at any point:

# yrbss_fn <- file.path( path.expand( "~" ) , "YRBSS" , "this_file.rds" )
# saveRDS( yrbss_df , file = yrbss_fn , compress = FALSE )

Load the same object:

# yrbss_df <- readRDS( yrbss_fn )

Survey Design Definition

Construct a complex sample survey design:

library(survey)

yrbss_design <- 
    svydesign( 
        ~ psu , 
        strata = ~ stratum , 
        data = yrbss_df , 
        weights = ~ weight , 
        nest = TRUE 
    )

Variable Recoding

Add new columns to the data set:

yrbss_design <- 
    update( 
        yrbss_design , 
        did_not_always_wear_seat_belt = as.numeric( qn8 == 1 ) ,
        ever_used_marijuana = as.numeric( qn46 == 1 ) ,
        tried_to_quit_tobacco_past_year = as.numeric( qn40 == 1 ) ,
        used_tobacco_past_year = as.numeric( q40 > 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( yrbss_design , "sampling" ) != 0 )

svyby( ~ one , ~ ever_used_marijuana , yrbss_design , unwtd.count )

Weighted Counts

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

svytotal( ~ one , yrbss_design )

svyby( ~ one , ~ ever_used_marijuana , yrbss_design , svytotal )

Descriptive Statistics

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

svymean( ~ bmipct , yrbss_design , na.rm = TRUE )

svyby( ~ bmipct , ~ ever_used_marijuana , yrbss_design , svymean , na.rm = TRUE )

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

svymean( ~ q2 , yrbss_design , na.rm = TRUE )

svyby( ~ q2 , ~ ever_used_marijuana , yrbss_design , svymean , na.rm = TRUE )

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

svytotal( ~ bmipct , yrbss_design , na.rm = TRUE )

svyby( ~ bmipct , ~ ever_used_marijuana , yrbss_design , svytotal , na.rm = TRUE )

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

svytotal( ~ q2 , yrbss_design , na.rm = TRUE )

svyby( ~ q2 , ~ ever_used_marijuana , yrbss_design , svytotal , na.rm = TRUE )

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

svyquantile( ~ bmipct , yrbss_design , 0.5 , na.rm = TRUE )

svyby( 
    ~ bmipct , 
    ~ ever_used_marijuana , 
    yrbss_design , 
    svyquantile , 
    0.5 ,
    ci = TRUE , na.rm = TRUE
)

Estimate a ratio:

svyratio( 
    numerator = ~ tried_to_quit_tobacco_past_year , 
    denominator = ~ used_tobacco_past_year , 
    yrbss_design ,
    na.rm = TRUE
)

Subsetting

Restrict the survey design to youths who ever drank alcohol:

sub_yrbss_design <- subset( yrbss_design , qn40 > 1 )

Calculate the mean (average) of this subset:

svymean( ~ bmipct , sub_yrbss_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( ~ bmipct , yrbss_design , na.rm = TRUE )

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

grouped_result <-
    svyby( 
        ~ bmipct , 
        ~ ever_used_marijuana , 
        yrbss_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( yrbss_design )

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

svyvar( ~ bmipct , yrbss_design , na.rm = TRUE )

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

# SRS without replacement
svymean( ~ bmipct , yrbss_design , na.rm = TRUE , deff = TRUE )

# SRS with replacement
svymean( ~ bmipct , yrbss_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( ~ did_not_always_wear_seat_belt , yrbss_design ,
    method = "likelihood" , na.rm = TRUE )

Regression Models and Tests of Association

Perform a design-based t-test:

svyttest( bmipct ~ did_not_always_wear_seat_belt , yrbss_design )

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

svychisq( 
    ~ did_not_always_wear_seat_belt + q2 , 
    yrbss_design 
)

Perform a survey-weighted generalized linear model:

glm_result <- 
    svyglm( 
        bmipct ~ did_not_always_wear_seat_belt + q2 , 
        yrbss_design 
    )

summary( glm_result )

Replication Example

This example matches statistics, standard errors, and confidence intervals from the “did not always wear a seat belt” row of PDF page 29 of this CDC analysis software document:

unwtd_count_result <-
    unwtd.count( ~ did_not_always_wear_seat_belt , yrbss_design )

stopifnot( coef( unwtd_count_result ) == 15071 )

wtd_n_result <-
    svytotal( 
        ~ one , 
        subset(
            yrbss_design , 
            !is.na( did_not_always_wear_seat_belt ) 
        )
    )

stopifnot( round( coef( wtd_n_result ) , 0 ) == 16917 )

share_result <-
    svymean(
        ~ did_not_always_wear_seat_belt ,
        yrbss_design ,
        na.rm = TRUE 
    )

stopifnot( round( coef( share_result ) , 4 ) == .3958 )

stopifnot( round( SE( share_result ) , 4 ) == .0172 )

ci_result <-
    svyciprop(
        ~ did_not_always_wear_seat_belt ,
        yrbss_design , 
        na.rm = TRUE
    )

stopifnot( round( confint( ci_result )[1] , 4 ) == 0.3621 )

stopifnot( round( confint( ci_result )[2] , 4 ) == 0.4304 )

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 YRBSS users, this code replicates previously-presented examples:

library(srvyr)
yrbss_srvyr_design <- as_survey( yrbss_design )