The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » General » Couples do not agree on marital status
Couples do not agree on marital status [message #24267] Thu, 07 April 2022 22:52 Go to next message
Sulo is currently offline  Sulo
Messages: 2
Registered: March 2022
Hi everyone, I am trying to analyze the couple's data of the Uganda 2016 dataset and have merged MR and IR by mv001=v001, mv002=v002, mv003=v034(woman's partner). However, I found out that some couples did not agree on whether they were married or living together. I even found some men reporting being single/divorced while women reported being married/living together with them. I wonder if anyone has met this issue, and what could be the cause?

Also, although I intend to include all couples that reported either being married or living together in my analysis, I wonder if I should do something regarding the disagreement?

Thank you all in advance!
Re: Couples do not agree on marital status [message #24304 is a reply to message #24267] Fri, 15 April 2022 16:02 Go to previous message
admin is currently offline  admin
Messages: 50
Registered: November 2012
Senior Member
Following is response from DHS Research & Data Analysis Director, Tom Pullum:

DHS prepares a CR (couples) file for every survey that includes an MR file. It consists of women and men who agree in their identification of each other, based on v034 for the woman and mv034* for the man.

Your procedure identifies women and men in the same household who do not name each other as the partner or say they are not currently married. There are a few cases like this in most surveys. Some may be errors, due to misunderstanding of the question or interviewer mistakes, but probably some are not errors. In any case, I recommend that you compare your file with the CR file, which is constructed consistently for every survey. I hope other users have suggestions.

We now have repositories of code written in Stata and SPSS available on Github. Please reference these code repositories as a resource for code for matching or calculating DHS indicators. The code repositories can be found at:

Previous Topic: Inclusion criteria for intimate partner violence questions
Next Topic: Median age at first marriage- Afghanistan 2015
Goto Forum:

Current Time: Sun Mar 3 18:48:20 Coordinated Universal Time 2024