The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Weighting data » Weights for Infant Mortality
Weights for Infant Mortality [message #12706] Sun, 02 July 2017 12:48 Go to next message
shampaisi is currently offline  shampaisi
Messages: 4
Registered: March 2013
I am trying to find the effect of political factors on infant mortality in India using NFHS 2. Since it is a child level regression I am wondering if I should use the women's weight V005 or divide V005 by the total number of children ever born (living or dead) and use this as sample weights in the regressions? Can you please clarify?

[Updated on: Sun, 02 July 2017 12:49]

Report message to a moderator

Re: Weights for Infant Mortality [message #12717 is a reply to message #12706] Mon, 03 July 2017 13:21 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3000
Registered: February 2013
Senior Member

Following is a response from Senior DHS Stata Specialist, Tom Pullum:

You would just use v005. The values of that variable are the same in the women's file (IR) and the children's file (KR or BR).
Previous Topic: Kenya DHS 2014; which sample weight to use?
Next Topic: Individual weight for PR data set
Goto Forum:

Current Time: Fri Mar 1 18:22:48 Coordinated Universal Time 2024