Home » Data » Weighting data » using wieght, cluster, strata
Re: using wieght, cluster, strata [message #26238 is a reply to message #26224] |
Tue, 21 February 2023 08:27 ![Go to previous message Go to previous message](/theme/default/images/up.png) |
Bridgette-DHS
Messages: 3151 Registered: February 2013
|
Senior Member |
|
|
Following is a response from Senior DHS staff member, Tom Pullum:
I assume you are using the KR files. These files contain the outcomes for children whose mothers are included in the survey, and virtually all of the mother's information is on the same records. For the Egypt 2014 survey, this file is EGKR61FL.dta. For the 2008 survey, replace "61" with "5A".
All regressions and other estimation commands should include svyset and svy, not just those with anthropometry variables. There have been many posting on the forum about svyset and svy. You can also read about them if you enter "help svyset" in Stata.
The svyset command for your data would be "svyset v021 [pweight=v005], strata(v023) singleunit(centered)". For most surveys, v001 and v021 are exactly the same, but for the Egypt surveys they are different and you should use v021, which is the PSU ID code. The sampling weights are v005 and the strata are v023. Then the estimation commands will begin with "svy: ".
There have been many DHS reports related to anthropometry. You can find them under the Publications tab and "Analytical" on the website. Also you can search for related posts on the forum.
Good luck!
|
|
|
Goto Forum:
Current Time: Sat Aug 31 09:16:03 Coordinated Universal Time 2024
|