The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Domestic Violence » Weights for Men's outcomes from the DV subsample (Are individual men's weight valid?)
Re: Weights for Men's outcomes from the DV subsample [message #27001 is a reply to message #26961] Thu, 08 June 2023 13:32 Go to previous messageGo to previous message
Janet-DHS is currently offline  Janet-DHS
Messages: 888
Registered: April 2022
Senior Member
Following is a response from DHS staff member, Tom Pullum:

Good question. In this analysis there would be some nonresponse from the women with respect to the DV module (on top of nonresponse to the women's interview), as well as nonresponse from the men with respect to the men's interview. A case could be made for calculating new weights that take both into account. However, I would not recommend this because it would be a lot of work for little return. The choice of weight usually has a negligible effect on the estimates and standard errors. (To clarify--it makes a big difference whether or not you use weights, but when there are alternatives, the effects are usually small.) I recommend that you use d005, and state this explicitly in your analysis. You could repeat some key results with mv005 to confirm that your conclusions are not affected.
 
Read Message
Read Message
Read Message
Previous Topic: Differences in observations in Original Stata file and Report
Next Topic: Sexual violence by anyone, non-partners, and intimate partners
Goto Forum:
  


Current Time: Sun Nov 24 22:38:27 Coordinated Universal Time 2024