The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Weighting data » analysing change over time and weights normalisation
analysing change over time and weights normalisation [message #25752] Mon, 05 December 2022 10:20 Go to next message
geoK is currently offline  geoK
Messages: 39
Registered: May 2014
Member
Hi all,
I am trying to replicate a similar type of analysis to this work published on BMJ (https://gh.bmj.com/content/7/4/e007798) where i want to study changes over time between NFHS-4 and NFHS-5 for a set of outcome variables and compare round 1 with round 2. I was wondering whether there is need to denormalise the weights at all as i will be working with 2 rounds of surveys. Many thanks.
Re: analysing change over time and weights normalisation [message #25761 is a reply to message #25752] Tue, 06 December 2022 08:39 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3017
Registered: February 2013
Senior Member

Following is a response from Senior DHS staff member, Tom Pullum:

What you propose is a comparison of two statistically independent samples. We recommend no changes to the weights.
Re: analysing change over time and weights normalisation [message #25764 is a reply to message #25761] Tue, 06 December 2022 11:48 Go to previous message
geoK is currently offline  geoK
Messages: 39
Registered: May 2014
Member
Many thanks.
Previous Topic: NFHS-5, when to calculate new weights?
Next Topic: Resampling data to obviate the need for weighting
Goto Forum:
  


Current Time: Thu Mar 28 16:03:09 Coordinated Universal Time 2024