The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Merging data files » ID variables for Children
ID variables for Children [message #10048] Mon, 20 June 2016 07:52 Go to next message
DHS user is currently offline  DHS user
Messages: 111
Registered: February 2013
Senior Member
I remember a couple of years ago I was told not to use just the caseid variable in the birth recode file so I created a unique id for each child: file_country_code file_dhs_phase caseid bidx

Out of curiosity, why do two kids (unique in terms of "id" or "uniqid") with the same caseid?

Re: ID variables for Children [message #10049 is a reply to message #10048] Mon, 20 June 2016 08:05 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3035
Registered: February 2013
Senior Member
Following is a response from Senior DHS Stata Specialist, Tom Pullum:

In the KR and BR files, "caseid" is the unique id code for the mother, constructed from v001, v002, and v003 (v003 is the woman's line number in the household files, that is, hvidx). caseid is the unique id for the woman, but not for her children, because a woman who has had children will often have had more than one. For the children in the KR and BRfiles, you need to use the combination of caseid (or v001, v002, v003) and bidx. bidx is 1 for the most recent child, 2 for the next most recent, etc. Hope that helps--let me know if you have other questions.

P.S. I suggest that you open a KR or BR file in Stata and enter something like this: "list caseid v001 v002 v003 bidx if _n<=100, table clean". This should show what I mean.
Previous Topic: What is the underlying criteria for merging datasets from various waves?
Next Topic: Merging DHS Files
Goto Forum:
  


Current Time: Fri Apr 19 23:24:38 Coordinated Universal Time 2024