The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Child Health » estimating stratum effect after pooling DHS databases
estimating stratum effect after pooling DHS databases [message #19671] Wed, 29 July 2020 12:21 Go to next message
slolib86 is currently offline  slolib86
Messages: 4
Registered: December 2017
Location: Peru
Dear all,

I am pooling three DHS database 2012-2014 from Peru, and after setting the data with these commands:

egen cluster=group(survey v021)
egen stratum= group(survey v024 v025)
svyset[pw=wgt], psu(v021) strata(stratum)

where: v021 is the PSU, v024 is regions, v025 is the type of residence urban/rural, v005 is the sample weight, and survey is the year

Is there a way to estimate the stratum effect or v025 covariate effect by GLM or OLS?

Thank you so much in advance

[Updated on: Sat, 01 August 2020 14:09]

Report message to a moderator

Re: estimating stratum effect after pooling DHS databases [message #19695 is a reply to message #19671] Tue, 04 August 2020 09:17 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3094
Registered: February 2013
Senior Member

Following is a response from DHS Research & Data Analysis Director, Tom Pullum:

I believe you are asking whether v025 can be included in a model even though it was included in svyset. Yes, you definitely can do that. The adjustments made by svyset do not affect the choice of covariates in any way.

Previous Topic: About the Data extraction
Next Topic: Trends in vaccination coverage and factors for complete vaccination
Goto Forum:

Current Time: Sun Jun 23 11:28:00 Coordinated Universal Time 2024