The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Mortality » Difference B/W Design Weight & Sample Weight
Difference B/W Design Weight & Sample Weight [message #21790] Mon, 21 December 2020 10:04 Go to next message
shujaat.smc@gmail.com is currently offline  shujaat.smc@gmail.com
Messages: 75
Registered: July 2020
Senior Member
Dear DHS Representative,

Is there any difference in design weight and sample weight?

The reason for asking this question is the following statement from Pakistan DHS Report 2017-18 in the section of sample weight "Design weights were adjusted for cluster-level non-response, household-level non-response, and individual non-response to get the sampling weights for women's and men's surveys respectively".

The Youtube videos on the DHS channel talks about the sample weight but after reading this statement I am not able to understand design weight.

Waiting for your kind reply. (This question has affected me to extent that I was
writing - weighting for your reply)

Best Regards

Dr. Hussain
Re: Difference B/W Design Weight & Sample Weight [message #21809 is a reply to message #21790] Wed, 23 December 2020 05:13 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2411
Registered: February 2013
Senior Member

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

I appreciate the pun! Design weights are the inverse of the sampling fractions (or inversely proportional to the sampling fractions). Those weights are then adjusted for non-response at different levels. The weights that are in the data files (hv005, v005, mv005) are the adjusted weights. We don't provide (and don't save) the original design weights. Your analysis should just use v005 (etc.).

Thanks for "weighting".


Re: Difference B/W Design Weight & Sample Weight [message #21817 is a reply to message #21809] Wed, 23 December 2020 08:24 Go to previous message
shujaat.smc@gmail.com is currently offline  shujaat.smc@gmail.com
Messages: 75
Registered: July 2020
Senior Member
Dear Tom Pullum,

Thanks a lot for your kind reply. Highly obliged!

Best Regards

Dr. Hussain
Previous Topic: Compensation for Omission and Displacement
Next Topic: Child mortality rates in Angola
Goto Forum:
  


Current Time: Wed Oct 27 06:58:43 Coordinated Universal Time 2021