The DHS Program User Forum      
Discussions regarding The DHS Program data and results
Home » Topics » Mortality » Weights in Mortality Estimation
Weights in Mortality Estimation [message #12226] Thu, 13 April 2017 02:59 Go to next message
Pmacharia is currently offline  Pmacharia
Messages: 1
Registered: April 2017
Location: Nairobi, Kenya

I am calculating under five mortality for Kenya using DHS data (women's file). I understand in order to correct for (non)response, stratification and survey design, I need to use weights.
This means that for Children dead and children ever born per mother I need to multiply this by the weight of the mother.

Is this correct interpretation?
Re: Weights in Mortality Estimation [message #12351 is a reply to message #12226] Wed, 03 May 2017 22:46 Go to previous message
Trevor-DHS is currently offline  Trevor-DHS
Messages: 536
Registered: January 2013
Senior Member
I suggest you follow the series of YouTube videos about sampling and weighting, and how to weight the data. See the tutorial videos, and watch :
Part I: Introduction to DHS Sampling Procedures
Part II: Introduction of Principles of DHS Sampling Weights
and then either:
Part III: Demonstration of How to Weight DHS Data in Stata, or
Part IV: Demonstration of How to Weight DHS Data in SPSS & SAS

In these videos you will learn how to weight the data for your analysis.
Next Topic: Maternal Mortality
Goto Forum:

Current Time: Thu Nov 23 04:02:58 Eastern Standard Time 2017