The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Reproductive Health » The Gambia DHS, 2013
The Gambia DHS, 2013 [message #10556] Fri, 05 August 2016 22:19 Go to next message
Jawla is currently offline  Jawla
Messages: 7
Registered: August 2016
Member
Hi DHS experts:

According to the DHS Household and Sampling Manual, the DHS surveys are two stage surveys. The sampling units for the first stage of selection is called the Primary Sampling Unit (PSU); the sampling unit for the second stage of selection is called the Secondary Sampling Unit (SSU).

This is the survey syntax for stratified two stage design from Stata 14 documentation:
svyset psu [pweight=weight], strata (strata) fpc (fpc1) || ssu, fpc (fpc2)
svyset v021 [pweight=v005], strata (v022) fpc (fpc1) || ssu, fpc (fpc2)

What is the secondary sampling unit(ssu) variable in DHS data set?

Any suggestion will be appreciated. Thanks


Best, Jawla.

[Updated on: Fri, 05 August 2016 22:25]

Report message to a moderator

Re: The Gambia DHS, 2013 [message #10557 is a reply to message #10556] Sun, 07 August 2016 15:59 Go to previous messageGo to next message
Jawla is currently offline  Jawla
Messages: 7
Registered: August 2016
Member
I am assuming that I might have to merge the women's data set and that of HH data set to be able to use the ssu(which I think is the household). Right?

Best, Jawla.
Re: The Gambia DHS, 2013 [message #10597 is a reply to message #10557] Mon, 15 August 2016 10:17 Go to previous messageGo to next message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
Dear User,
A response from Dr. Ruilin Ren, sampling expert:
Quote:

In the STATA survey set, you need to declare the PSU (DHS variable V001 or V021), but not necessary to declare the SSU (DHS variable V002), if your aim is to produce sampling errors. You do not need to declare the fpc because it is not provided in the DHS data.
Re: The Gambia DHS, 2013 [message #10626 is a reply to message #10597] Sun, 21 August 2016 23:48 Go to previous messageGo to next message
Jawla is currently offline  Jawla
Messages: 7
Registered: August 2016
Member
Thanks Dr. Ruilin for your kind answer to my question. Is very much appreciated!
Best, Jawla.


Best, Jawla.
Re: The Gambia DHS, 2013 [message #13137 is a reply to message #10597] Tue, 26 September 2017 15:03 Go to previous messageGo to next message
ab803 is currently offline  ab803
Messages: 6
Registered: September 2017
Member
Hi Dr. Ren,

If the FPC is not provided, how do we set up the second stage, which requires an FPC for stata to recognize it. I'm trying to account for the fact that multiple children are selected from a household (and are non-independent), but am unable to set up hv002 as ssu.

Many thanks!
Re: The Gambia DHS, 2013 [message #13260 is a reply to message #13137] Tue, 10 October 2017 08:45 Go to previous messageGo to next message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
A response from technical expert, Dr. Tom Pullum:
Quote:

As has been noted in other posts, we are unable to separate out the probabilities of selection for the cluster (v001 or v021)) and the household (v002). What we have is the product (the second probability is conditional on the selection of a cluster). There is no way to separate the two. That's unfortunate, and it means that svyset cannot be properly constructed for multi-level models. The basic reason for this is that if the separate probabilities were available, then the first one, with a little additional information, would allow one to identify the PSU. DHS does everything possible to protect the privacy and confidentiality of the respondents. Apart from that, the required information is deleted after the weights have been constructed. We couldn't retrieve it even if we wanted to.



Re: The Gambia DHS, 2013 [message #13489 is a reply to message #13260] Fri, 10 November 2017 00:55 Go to previous messageGo to next message
ab803 is currently offline  ab803
Messages: 6
Registered: September 2017
Member
Thank you so much, this is really helpful!

Any advice on how to account for the clustering of multiple children within a household?

With gratitude!
Re: The Gambia DHS, 2013 [message #13611 is a reply to message #13489] Wed, 29 November 2017 10:59 Go to previous message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
Dr. Tom Pullum responded:
Quote:

There is definitely some clustering of child-level outcomes by the mother and/or household. At DHS we do not adjust for that, but you certainly may want to do so. A complication is that the number of children per woman is low, especially if you are focusing on outcomes within a recent time period and on children in a narrow age range such as 0-4. Other users may be able to suggest how to specify svyset for such outcomes.
Previous Topic: Filter in question #343
Next Topic: Antenatal care and current pregnancy
Goto Forum:
  


Current Time: Thu Mar 28 15:43:07 Coordinated Universal Time 2024