The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » Nigeria » Matching Individual and Household Recode
Matching Individual and Household Recode [message #2438] Wed, 18 June 2014 09:49 Go to next message
skyb is currently offline  skyb
Messages: 1
Registered: June 2014
Location: Switzerland
In the DHS 2008 of Nigeria I want to match the household and individual recode in order to have certain variables in the household recode.

Now if I just keep v001 and v002 in the individual recode (just households) and drop all the duplicates and rename them as hv001 and hv002 and match the household recode with the individual recode in Stata 1:m (one to many) only 24272 observations are matched. 9798 observations in the household recode are not matched with the households from the individual recode.

Why do not all of the households match? Is it because the rest of the observations stem from the male recode?

Thanks for the clarification.
Re: Matching Individual and Household Recode [message #2472 is a reply to message #2438] Tue, 24 June 2014 16:59 Go to previous messageGo to next message
Messages: 1516
Registered: February 2013
Senior Member
Dear User,
Can you please be more specific about what you are trying to accomplish? Most of the tables in our final report are based on weighted numbers unless otherwise stated. Thank you!
Re: Matching Individual and Household Recode [message #14613 is a reply to message #2438] Sun, 22 April 2018 17:12 Go to previous message
kingx025 is currently offline  kingx025
Messages: 95
Registered: August 2016
Location: Minneapolis. Minnesota
Senior Member
I'm not sure that I'm answering this question, but maybe these points will help.

First, households in the DHS are randomly selected from survey areas, regardless of whether they include women of childbearing age. By contrast, the IR files are limited to women of childbearing age. So there are lots of households that don't contain women of the appropriate age to link to the IR files.

Second, maybe I can save you some merging work. IPUMS-DHS, which includes all the Nigerian DHS surveys, has done some advance merging, linking household records to IR women's files and then linking the household and women's data to the KR child and BR birth files. If you want to know summary household characteristics from the household data but use women from the IR files as your unit of analysis, you can do that using IPUMS-DHS data and picking women as the unit of analysis.

We have not yet merged the women's records back to the household member or hierarchical household files, so if that was your goal, I can't help for now.

Miriam King

Dr. Miriam King
IPUMS-DHS Project Manager (
Previous Topic: Inaccessibility of DHS Data Set, 1990
Next Topic: create female autonomy index
Goto Forum:

Current Time: Thu Jun 20 19:11:55 Coordinated Universal Time 2024