The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » Ethiopia » multi level analysis on low birth weight (how to aggregate community level variebles from individual level variables)
multi level analysis on low birth weight [message #16666] Thu, 14 February 2019 06:23 Go to next message
alemneh is currently offline  alemneh
Messages: 1
Registered: February 2019
hello forum users,i am planning to apply multilevel analysis to identify individual and community level factors by EDHS data.
but i can't access some of community level variables directly from dataset.therefore i need to aggregate individual level variables to community levelvariables such as community illiteracy level community poverty level etc.but i face achalenge just how to apply stata code.therefore i need support from an expert in this area.thank you in advance.
Re: multi level analysis on low birth weight [message #16834 is a reply to message #16666] Thu, 07 March 2019 12:30 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3115
Registered: February 2013
Senior Member

Following is a response by Senior DHS Stata Specialist, Tom Pullum:

I know of two ways to attach cluster-level compositional variables (such as proportion of the women in the cluster who are in the bottom wealth quintile) to the individual records. The first is to (a) construct the compositional variable with "collapse....., by(v001)" and then (b) merge that cluster-level file back to the individual-level data. The other possibility would be to use some of the "egen....,by(v001)" commands. I suggest that you try one or the other of these approaches. Let us know if you have trouble.

Previous Topic: Interview date
Next Topic: Duplicating EDHS resuls using STATA
Goto Forum:

Current Time: Mon Jul 22 06:06:09 Coordinated Universal Time 2024