The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Merging data files » How to weight merged PR and IR files- Afghanistan DHS (Merging PR and IR files)
How to weight merged PR and IR files- Afghanistan DHS [message #24163] Mon, 07 March 2022 10:13 Go to next message
Sara Rahim is currently offline  Sara Rahim
Messages: 4
Registered: January 2022
Member
Hello. I am using the DHS 2015 Afghanistan data.

I am interested in making a compilation of all women between the age of 14-49, including those who qualify for ever-married survey as well as those who didn't qualify and were never married. I merged the PR file with the IR file for all women, to get the characteristics of the ever-married women from the IR file, particularly age of first cohabitation.

The PR file has the household sample weight (hv005), and the IR file has the women's individual sample (v005) for those who qualify. Can you give me some guidance on how I should proceed with the sample weighting? Should I just use the household sample weight for all women?

Thank you
Re: How to weight merged PR and IR files- Afghanistan DHS [message #24169 is a reply to message #24163] Tue, 08 March 2022 06:34 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3017
Registered: February 2013
Senior Member

Following is a response from DHS Senior Sampling Specialist, Mahmoud Elkasabi:

Since you are interested in all women 15-49, you can use the household weight (hv005) for your analysis.

Re: How to weight merged PR and IR files- Afghanistan DHS [message #24221 is a reply to message #24169] Fri, 18 March 2022 19:31 Go to previous messageGo to next message
Sara Rahim is currently offline  Sara Rahim
Messages: 4
Registered: January 2022
Member
Thank you for the reply. I have one more question:

Suppose I were to only use the IR file with individual women weights v005, and want to drop some women, e.g. the oldest cohort or some women who married before a certain a year. Does the dropping of some women mean I can no longer use v005 as weights? Can I proceed with the remaining observations normally?

Appreciate any help on this.


Thank you
Re: How to weight merged PR and IR files- Afghanistan DHS [message #24228 is a reply to message #24221] Mon, 21 March 2022 16:28 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3017
Registered: February 2013
Senior Member

Following is another response from DHS Senior Sampling Specialist, Mahmoud Elkasabi:

You can do any analysis on any subset with no need to change the weight, v005 in this case.
Previous Topic: Couple file from male and female dataset
Next Topic: Merging KR dataset for Ethiopia to CR dataset
Goto Forum:
  


Current Time: Fri Mar 29 10:25:06 Coordinated Universal Time 2024