The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » General » Young Adult Reproductive Health Survey
Young Adult Reproductive Health Survey [message #22679] Tue, 20 April 2021 10:03 Go to next message
dredtoe is currently offline  dredtoe
Messages: 2
Registered: April 2021
Member
Hello, I tried to analyze the pre marital sex among young adult . At first I used MR data set but all the sample count as married or living with spouse. Then, I am using the special data set IDML7AFL. I tried to calculate it and compare my finding with the adolescent report but it comes out different. Can anyone explaine what is special data set and what should I do to get the same result as the report ?
Is there any special treatment when using the special data set ?
  • Attachment: COMPARE.PNG
    (Size: 128.21KB, Downloaded 30 times)
Re: Young Adult Reproductive Health Survey [message #22704 is a reply to message #22679] Fri, 23 April 2021 07:52 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2312
Registered: February 2013
Senior Member

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

The main purpose of the weight variable is to produce unbiased estimates that are adjusted for the sample design. Usually the smaller strata are over-sampled (so they have weights <1) )and the larger strata are under-sampled (and have weights>1). On the average the weight (after dividing by 1 million) is 1.

Sometimes the weighted number will be larger than the unweighted number and sometimes it will be smaller. It just depends on how your cases for a particular outcome are distributed across the strata. So I don't think you have a problem.
Re: Young Adult Reproductive Health Survey [message #22705 is a reply to message #22704] Fri, 23 April 2021 08:11 Go to previous message
dredtoe is currently offline  dredtoe
Messages: 2
Registered: April 2021
Member
Hello, thank you for your information now i realize what went wrong and how i got smaller sample size after the weighted.
Previous Topic: Educational attainment classification
Next Topic: Cousin's marriages
Goto Forum:
  


Current Time: Mon Jun 21 21:46:37 Coordinated Universal Time 2021