Proper survey weight to use?

HEALTH SURVEYS
1

I noticed some changes in the documentation for certain variables I’m interested in using for analysis and wanted some clarification on the proper survey weights to use.

I’m pooling data from the IPUMS MEPS survey from 2008-2023, and one of my variables of interest is CANCEREV. Previously, I saw on the variable documentation tab that PERWEIGHT should be used for this variable and have built my analysis around this weight. However, after recently revisiting the website, I noticed that this has changed to using PERWEIGHT for 2008-2017 and SAQWEIGHT for 2018-2023. Similarly, other variables like AGE and SEX have also change their weight guidance to use SAQWEIGHT for 2018-2023.

Since the data I have was pulled prior to this change, should I stick with using PERWEIGHT, or should I follow the new guidance and use SAQWEIGHT? Would I use SAQWEIGHT for all the years (2008-2023)? Do I need to request a new data pull?

Thanks!

1 Like
2

Thank you for bringing this issue to our attention. After discussing with my colleagues on the data team, it appears that this recent change to recommended weights occurred inadvertently when food security module weights were added on 1/26/26 (see the revision history note). The website has been updated to again display the correct weights that should be used (e.g., PERWEIGHT for CANCEREV for 2008-2023).