The DHS Program User Forum: Weighting data » Clustered Standard Errors

Home » Data » Weighting data » Clustered Standard Errors

Show: Today's Messages :: Show Polls :: Message Navigator

Re: Clustered Standard Errors [message #22298 is a reply to message #22292]

Wed, 24 February 2021 09:01

Bridgette-DHS
Messages: 3230
Registered: February 2013

Senior Member

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

The generic form of svyset is this:

svyset cluster_ID [pweight=v005], strata(stratum_ID) singleunit(centered)

In this syntax, the first variable after "svyset" (here "cluster_ID") is the PSU. "singleunit(centered)" is related to the "strata(stratum_ID)" term. It keeps the program from crashing if it encounters only one PSU within a stratum. There are a couple of alternatives to "centered" but I have done comparisons and the results are indistinguishable for the different options. You are usually ok without the singleunit option but I usually include it because I hate crashes.

Below I will paste an example from one time when I was pooling two surveys from 2008 and 2018. The two surveys had different specifications of strata. You can see how "egen group" was used. Note that "egen group" does NOT combine or pool. It does just the opposite. For example, say that in the PR file you wanted to construct a variable for all combinations of urban/rural (hv025=1 or 2) and male/female (hv104=1 or 2). You would use "egen place_sex=egen(hv025 hv104)" to get a four-category variable for the combinations of hv025 and hv104. This can be handy for making tables or interpreting interaction terms. In the example below, it basically distinguishes the designs of the 2008 and 2018 samples. Hope this helps.

* In the 2008 survey
egen stratum_ID_2008=group(shstate v025)
gen tempvar=stratum_ID_2008

* In the 2018 survey
gen stratum_ID_2018=v023
gen tempvar=stratum_ID_2018

* Append, and construct "survey" using v007...

* In the combined file
egen stratum_ID=group(tempvar survey)
drop tempvar

egen cluster_ID=group(v001 survey)

svyset cluster_ID [pweight=v005], strata(stratum_ID) singleunit(centered)

Report message to a moderator

[Message index]

		Clustered Standard Errors By: cbdolan on Thu, 25 February 2016 13:10
		Re: Clustered Standard Errors By: Bridgette-DHS on Wed, 02 March 2016 11:57
		Re: Clustered Standard Errors By: analyst_till on Wed, 03 February 2021 11:09
		Re: Clustered Standard Errors By: Bridgette-DHS on Fri, 05 February 2021 09:32
		Re: Clustered Standard Errors By: analyst_till on Fri, 05 February 2021 11:01
		Re: Clustered Standard Errors By: Bridgette-DHS on Mon, 08 February 2021 08:17
		Re: Clustered Standard Errors By: analyst_till on Tue, 09 February 2021 05:04
		Re: Clustered Standard Errors By: Bridgette-DHS on Tue, 09 February 2021 08:49
		Re: Clustered Standard Errors By: analyst_till on Tue, 09 February 2021 12:24
		Re: Clustered Standard Errors By: Bridgette-DHS on Wed, 17 February 2021 09:00
		Re: Clustered Standard Errors By: analyst_till on Mon, 22 February 2021 09:50
		Re: Clustered Standard Errors By: Bridgette-DHS on Tue, 23 February 2021 07:08
		Re: Clustered Standard Errors By: analyst_till on Tue, 23 February 2021 12:12
		Re: Clustered Standard Errors By: analyst_till on Wed, 24 February 2021 08:09
		Re: Clustered Standard Errors By: Bridgette-DHS on Wed, 24 February 2021 09:01
		Re: Clustered Standard Errors By: analyst_till on Wed, 24 February 2021 09:42
		Re: Clustered Standard Errors By: Bridgette-DHS on Wed, 24 February 2021 10:09
		Re: Clustered Standard Errors By: analyst_till on Wed, 24 February 2021 10:38
		Re: Clustered Standard Errors By: id709nvz on Thu, 24 March 2022 19:57
		Re: Clustered Standard Errors By: analyst_till on Sat, 26 March 2022 05:30
		Re: Clustered Standard Errors By: id709nvz on Thu, 01 September 2022 12:52

Previous Topic:	Confirming correct survey design
Next Topic:	What is the difference between v005 and sweight DHS India?

Goto Forum:

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Tue Jan 20 05:44:01 Coordinated Universal Time 2026