The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Weighting data » weighting data
weighting data [message #30345] Sun, 10 November 2024 04:01 Go to next message
Hejie Wang is currently offline  Hejie Wang
Messages: 19
Registered: July 2024
Member
I have a question about new weights for merged surveys, my idea is to multiply the proportion of each survey to the merged file by the weight of that observation (wt), is this the right thing to do?

This R code is here:
data$wt<-data$v005/100000
survey_counts <- table(data$v000)
total_samples <- nrow(data)
survey_proportions <- survey_counts / total_samples
data$survey_proportion <- survey_proportions[data$v000]

Can you give me some advice about this weighting?

Report message to a moderator

Re: weighting data [message #30351 is a reply to message #30345] Mon, 11 November 2024 14:09 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3230
Registered: February 2013
Senior Member
All of your questions have been asked and answered earlier on the forum.

Report message to a moderator

Re: weighting data [message #31808 is a reply to message #30345] Thu, 12 March 2026 03:36 Go to previous message
JeanEdmonson is currently offline  JeanEdmonson
Messages: 1
Registered: March 2026
Member
@escape tsunami for brainrots Need to rescale or denormalize weights according to DHS standard method when combining multiple surveys.

[Updated on: Fri, 13 March 2026 04:08]

Report message to a moderator

Previous Topic: Pooled weights for men and women sample.
Next Topic: Missing child labor weight variable
Goto Forum:
  

[ Syndicate this forum (XML) ] [ RSS ] [ PDF ]

Current Time: Thu May 14 08:42:51 Coordinated Universal Time 2026
.:: Contact :: Home :: Privacy Policy ::.

Powered by: FUDforum 3.0.9.
Copyright ©2001-2018 FUDforum Bulletin Board Software