The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Water and Sanitation » Source of drinking water and toilet facility
Source of drinking water and toilet facility [message #12779] Wed, 12 July 2017 12:23 Go to next message
Shek is currently offline  Shek
Messages: 19
Registered: November 2014
I am working on childhood diarrhea. Source of drinking water and toilet facility are part of my explanatory variables, from a previous post, i was made to understand that "source of drinking water and toilet facility are produced by merging the household recode (HR) dataset with the kid's recode (KR) dataset and recoding the source of drinking water and toilet facility variables according to the rules in table 2.1 and 2.2. and that these are not based just on v113 and v116 as these variables exclude non de jure (non usual) residents".

-I am using the Kids recode (KR) data set and i do not want to merge my dataset with the household recode(HR). Is it okay if i use v113 and v116 and treat "not a dejure resident" as "missing".

Re: Source of drinking water and toilet facility [message #14568 is a reply to message #12779] Sat, 21 April 2018 20:34 Go to previous message
kingx025 is currently offline  kingx025
Messages: 95
Registered: August 2016
Location: Minneapolis. Minnesota
Senior Member
I think you could exclude the "not de jure resident" cases as missing. After all, the questions about the source of water and toilet facility relate to the physical household dwelling that was interviewed; in general, we don't know what were the water and sewage arrangements back home for the temporary visitors. If you follow this practice, you might want to exclude cases that were coded as "visitors" rather than "regular household members" using the V135 (RESIDENT) variable.

If you don't want to deal with merging the household record to the child record, you can get the household level variables while still working with data from the KR file if you make your data file from IPUMS-DHS (at The IPUMS-DHS staff have merged the household record to the woman's record and then merged the mother's record to the child record in the KR file, so you can get all household and mother's characteristics as variable with no merging yourself, if you select "children" as your unit of analysis in IPUMS-DHS. Just log in with your DHS user email and password to make a customized data file with the samples and variable you want, with no need to merge across file types.

Miriam King

Dr. Miriam King
IPUMS-DHS Project Manager (
Previous Topic: Water-borne diseases in DHS
Next Topic: Childhood nutritional status
Goto Forum:

Current Time: Sun Jun 23 03:26:29 Coordinated Universal Time 2024