The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Weighting data » Applying weights for HIV Prevalence (Applying weights for HIV Prevalence on merged IR and AR file (Lesotho,2014))
Applying weights for HIV Prevalence [message #19665] Tue, 28 July 2020 08:43 Go to next message
User53787 is currently offline  User53787
Messages: 1
Registered: July 2020
Member
Hello,

I have merged the AR file with the IR file for Lesotho 2014 on SPSS. My questions are;

1. When applying the weights for analysis in SPSS, should I use the command, "compute WGT=V005/1000000." as suggested in the dhs videos or I should use the (HIV05) variable instead.

2. After the weights have been applied, how do i calculate HIV Prevalence in SPSS to arrive at the 30% written in the Lesotho 2014 final report (if i could get the syntax, if possible).

3. How do I then calculate HIV Prevalence by, say, Age and region (also in SPSS).


Any help will be greatly appreciated.
Re: Applying weights for HIV Prevalence [message #19719 is a reply to message #19665] Wed, 05 August 2020 08:49 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3210
Registered: February 2013
Senior Member

Following is a response from DHS Research & Data Analysis Director, Tom Pullum:

When using the AR data, specifically the test outcome variable HIV03, you should definitely use HIV05, not V005, as the weight.

HIV prevalence is the percentage of tested cases for which the HIV03 is 1. Indeterminate test results are included in the denominator.

The DHS staff cannot help with SPSS syntax, unfortunately. Perhaps another user can help.
Previous Topic: How to Weight Data in R
Next Topic: Sample weights for blood pressure data
Goto Forum:
  


Current Time: Fri Dec 13 15:31:15 Coordinated Universal Time 2024