The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Dataset use (other programs) » Mixed effect models with complex survey design R (Mixed effect models with complex survey design R)
Mixed effect models with complex survey design R [message #22309] Thu, 25 February 2021 07:26 Go to next message
asya_dm is currently offline  asya_dm
Messages: 2
Registered: February 2021
Member
I would like to use the NFHS-4 data for India for doing a linear regression with random effects for districts. From what I have read in the forum I need to account both for the survey weights and for the complex survey design (stratification) to ensure my effect estimates are correct and the standard errors robust. Explanations on the survey package in R on the DHS website have been very helpful. However, I struggle to find any information on how to run a linear regression with random effects accounting for complex survey design in R, something similar to the lmer function in the lmer4 package in R. Does anyone have any experience with that? Any help wll be greatly appreciated.
Re: Mixed effect models with complex survey design R [message #22312 is a reply to message #22309] Thu, 25 February 2021 09:53 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2265
Registered: February 2013
Senior Member

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

This question goes beyond what the DHS staff can answer. Hope other forum users can help.

Previous Topic: How to calculate the prevalence of an outcome by SAS for ever married women surveys?
Goto Forum:
  


Current Time: Thu May 6 06:16:43 Coordinated Universal Time 2021