Population Assessment of Tobacco and Health

Weighted variable for W2 + W3 Tips for Using the PATH Study Data User Forum

Return to the Population Assessment of Tobacco and Health (PATH) Study Series page.

2 posts / 0 new
Last post
John Lee
Weighted variable for W2 + W3

Hello,

Just want to make sure which weighted variable should be used for the analysis in Wave 2 + Wave 3 merged dataset?

As indicated: "The all-waves weights file is for respondents who have participated in all three waves of data collection. The single-wave weights file is for all respondents in Wave 3 regardless of their participation in Wave 2." However, I'm not so sure which weight variable should be used for W2 + W3 dataset? 

In addition, when we consider the "missing observation" (i.e., those who completed in Wave 1, but not Wave 2 or Wave 3) in the merged dataset (W1+W2+W3), which weight variable should be appropriate? Current weighted variables do not take account for missing observation, am I correct?

Sorry for silly questions, but please let me know!

Thanks,

John

clairece
In both scenarios, Wave 3 all

In both scenarios, Wave 3 all-waves weights should be used. These weights account for missing observations resulting from missing a full interview, but not missing observations resulting from not responding to a particular question in the interview.

Claire Cepuran

National Addiction and HIV Data Archive Program
Inter-university Consortium for Political
  and Social Research (ICPSR)
734-615-1959

Log in or register to post comments