guest post by my friend thomas yokota, an oahu-based epidemiologist. palmero professor vito muggeo wrote the joinpoint analysis section of the code below to demonstrate that the segmented package eliminates the need for external (registration-only, windows-only) software. survey package creator and professor thomas lumley wrote the svypredmarg function to replicate SUDAAN’s PREDMARG command and match the cdc to the decimal. richard lowry, m.d. at the centers for disease control & prevention wrote the original linear trend analysis then answered our infinite questions. biquadratic thanks.
The purpose of this analysis is to make statements such as, “there was a significant linear decrease in the prevalence of high school aged americans who have ever smoked a cigarette across the period 1999-2011” with complex sample survey data.
This step-by-step walkthrough exactly reproduces the statistics presented in the Center for Disease Control & Prevention’s (CDC) linear trend analysis, using free and open source methods rather than proprietary or restricted software.
The example below displays only linearized designs (created with the svydesign function). For more detail about how to reproduce this analysis with a replicate-weighted design (created with the svrepdesign function), see note below section #4.
(1) Data Importation
Prior to running this analysis script, the Youth Risk Behavioral Surveillance System (YRBSS) 1991-2011 single-year files must all be loaded as R data files (.rda) on your local machine. Running the download automation script will create the appropriate files. If you need assistance with the data-loading step, first review the main YRBSS blog post.
# setInternet2( FALSE ) # # only windows users need this line
# library(downloader)
# setwd( "C:/My Directory/YRBSS/" )
# source_url( "https://raw.github.com/ajdamico/asdfree/master/Youth%20Risk%20Behavior%20Surveillance%20System/download%20all%20microdata.R" , prompt = FALSE , echo = TRUE )
(2) Load Required …read more
Source:: r-bloggers.com