The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Weighting data » weighting in chi-square test?
weighting in chi-square test? [message #12992] Sun, 03 September 2017 08:46 Go to next message
PintuPaul is currently offline  PintuPaul
Messages: 13
Registered: September 2017
Location: New Delhi, India
Member
Hi,
I am confused using sample weight in bivariate analysis. Is it we need to use weight in chi-square test? or we just can test without using sample weight? I am using 'tabout' command in stata and when I am using sample weight in chi-square test the value of chi2 goes down and the value of chi2 is pretty high without weight. I am asking which one is appropriate when we do chi2 test in bivariate analysis?
Thank you!


M.Phil. Researcher
Centre for the Study of Regional Development
School of Social Science
Jawaharlal Nehru University
New Delhi-110067
India
Re: weighting in chi-square test? [message #13052 is a reply to message #12992] Mon, 11 September 2017 13:44 Go to previous message
Reduced-For(u)m
Messages: 292
Registered: March 2013
Senior Member

In general, if you want to make inferences on population-level parameters (which it sounds like you want, given your tabout), you need to weight.

I'm surprised a bit that it matters a lot though. Are you adjusting for survey design (clustering, stratification) in both cases? It maybe also depends on which variables you are testing, because some outcomes require special weights.
Previous Topic: Use of svyset when standard errors are already clustered
Next Topic: Weights for analysis of HIV+/HIV- urban and rural populations
Goto Forum:
  


Current Time: Thu Dec 12 22:26:59 Coordinated Universal Time 2024