The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Mortality » Neonatal Mortality for India using NFHS 5 data
Neonatal Mortality for India using NFHS 5 data [message #24407] Tue, 10 May 2022 14:58 Go to next message
Aritro2506 is currently offline  Aritro2506
Messages: 1
Registered: May 2022
Hello Members,

I am trying to enumerate the number of neonatal deaths (within 28 days of birth) for each of the districts across all states and union territories in India, using NFHS 5 data. I am using the births file and the variable I am working with is b6 (age at death). How should I recode the selected variable and what should be the sample weights used ? I am using STATA 14 as my analysis software.

Any help would be appreciated!

[Updated on: Tue, 10 May 2022 14:59]

Report message to a moderator

Re: Neonatal Mortality for India using NFHS 5 data [message #24427 is a reply to message #24407] Fri, 13 May 2022 11:03 Go to previous message
Janet-DHS is currently offline  Janet-DHS
Messages: 37
Registered: April 2022
Following is response from DHS Research & Data Analysis Director, Tom Pullum:

The usual way to get this would be with the KR file for children born in the past 5 years. Enter "gen nndeath=0" and "replace nndeath=1 if b6<128". The mean of this variable will be a proportion; you can multiply a proportion by 1000 if you want neonatal deaths per 1000 births. Use the national weight, v005. I assume you have looked up the variables for states and union territories and districts. Someone can help you with the formatting of the results. You will have a lot of numbers to work with if you want an estimate for each district. You could use the "proportion" command, which will give confidence intervals.
Previous Topic: How to do Binary Logistic regression on Neonatal Mortality and Region
Goto Forum:

Current Time: Mon May 16 07:02:25 Coordinated Universal Time 2022