The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Dataset use in Stata » Relative index of inequality calculation
Relative index of inequality calculation [message #11195] Thu, 17 November 2016 02:16 Go to next message
zobidaislam is currently offline  zobidaislam
Messages: 6
Registered: March 2016
Location: Dhaka

I am using Pakistan DHS data (women's data). I want to estimate the relative index of inequality for antenatal care (Inequality based on wealth index). If I just use logistic regression model without adjusting for other factors, can I call it "relative index of inequality"?

If my dependent variable is anc (0=no, 1=yes) and the covariate is quintile (1=poorest, 2=poorer, 3=middle class, 4=richer, 5= richet)

The code is:
char quintile [omit] 1
logistic anc i.quintile

Thank you.

Re: Relative index of inequality calculation [message #11198 is a reply to message #11195] Thu, 17 November 2016 10:45 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2313
Registered: February 2013
Senior Member
Following is a response from Senior DHS Stata Specialist, Tom Pullum:


I assume that you are looking at Comparative Report 42, page 5, index 2. What you have described is correct, but be sure to use svyset and svy to adjust for the weights, clusters, and strata. You want the coefficient for the fifth quintile, without exponentiation.

Previous Topic: Tab2 using survey weights
Next Topic: File and variable in Madagascar 2013 MIS
Goto Forum:

Current Time: Wed Jun 23 13:03:44 Coordinated Universal Time 2021