The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Mortality » Very early neonatal mortality (Use of sampling weights for calculation of proportion of very early noenatal mortality )
Very early neonatal mortality [message #27050] Fri, 16 June 2023 10:07 Go to next message
asya_dm is currently offline  asya_dm
Messages: 4
Registered: February 2021
Member
Dear DHS Program Staff,

I would like to calculate very early neonatal mortality (babies that die on the same day they are born) as a share of total neonatal mortality (babies that die within 28 days from the day that they are born) using the Full Birth History questionnaire for India (DHS India 2015-16). Would it be correct to apply the sampling weight to get correct values? I am not sure if this would be meaningful since I will be applying them only to a sub-sample of all births, which would assume that the existing sampling weights are the same between this sub-sample and the whole sample.

Your help will be very much appreciated.

Kind regards,
Asya
Re: Very early neonatal mortality [message #27140 is a reply to message #27050] Tue, 20 June 2023 11:13 Go to previous message
Janet-DHS is currently offline  Janet-DHS
Messages: 888
Registered: April 2022
Senior Member
Following is a response from DHS staff member, Tom Pullum:

Glad you are using the data on early deaths given by b6. This information is under-utilized.

You do not need to change the sample weights. Even when the outcomes you analyze are relatively rare, the representativeness of the sample is not affected. And even if you reduce the sample, for example by restricting to rural births, the representativeness of the sample is not affected. You can leave the weight as they are.
Previous Topic: Maternal Mortality in Liberia
Next Topic: STILLBIRTH RATE
Goto Forum:
  


Current Time: Mon Nov 25 17:21:38 Coordinated Universal Time 2024