The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Sampling and Weighting Webinar June 2015 » Using weights in regression analysis
Using weights in regression analysis [message #4424] Mon, 25 May 2015 08:00 Go to next message
Valko is currently offline  Valko
Messages: 12
Registered: October 2014
Member
Dear Moderator,

I would like to raise a question about a necessity of using weights in logistic regression analysis. Since, in DHS user forum there was a post dated 20 February 2013 that stated that "Not using weights is a minority viewpoint here at DHS. Almost all of us now advocate the use of weights. How you use them will depend somewhat on your statistical package. Most of us here use Stata", I have few questions:

1) is this recommendation also applicable in SPSS?
2) What document can I cite for using weighting in the logistic regression in SPSS?
3) In SPSS, i selected the subsample of men with certain characteristics. From the entire sample of males i selected married men of certain age. Shall I still use the following code to this subsample of men? Pls see below:
COMPUTE WTVAR=MV005/1000000.
WEIGHT BY WTVAR.

best regards,
Valeriya
Re: Using weights in regression analysis [message #18672 is a reply to message #4424] Sat, 25 January 2020 12:38 Go to previous message
kindu is currently offline  kindu
Messages: 3
Registered: March 2019
Member
should weight applied as v005/1000000 for analyzing the IR file of one region? or is there another recommendation?
Previous Topic: Weighting for multi-country data
Next Topic: June 3rd Webinar Analyzing DHS Data: Weights and other adjustments for the survey design
Goto Forum:
  


Current Time: Tue Jul 14 17:46:05 Eastern Daylight Time 2020