The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Dataset use in Stata » Guidance regarding Gender Pooling in Liberia 2013 DHS data (Guidance regarding Gender Pooling)
Guidance regarding Gender Pooling in Liberia 2013 DHS data [message #19992] Fri, 11 September 2020 13:54 Go to next message
Miatta is currently offline  Miatta
Messages: 3
Registered: September 2020
Member
I am examining HIV testing behavior among men and women in Liberia, West Africa. 2013 Liberia Demographic and Health Survey men and women dataset: I would like to inquire about appending the men and women (unmarried persons) datasets together.
My question is how do I create accurate pooled weights (2013 Liberia DHS men and women data)? Do I need to also create a pooled strata and primary sampling unit (psu)? If so, any guidance will be appreciated. Many of posts in the forum discuss pooling multiple countries or years together but I am seeking guidance regarding gender pooling. What modifications will I need to make to the weights to get accurate results once the data has been appended? Thank you

Best, Miatta Dennis
Georgia Southern Univ DrPH Candidate

[Updated on: Fri, 11 September 2020 13:59]

Report message to a moderator

Re: Guidance regarding Gender Pooling in Liberia 2013 DHS data [message #19993 is a reply to message #19992] Fri, 11 September 2020 18:28 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2034
Registered: February 2013
Senior Member

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

You don't need to alter the weights at all. I would open the men's file, then enter "rename mv* v*" and "gen sex=1", then append the women's file, and enter "replace sex=2 if sex==.", "label define sex 1 "Man" 2 "Woman" " and "label values sex sex". I would define sex to be consistent with hv104 in the PR file. The IR labels will over-write the MR labels in the append because the last file in any set of appends will determine the variable and value labels. You should check your key variables; some may be different in the IR and MR files, which case you want to keep them as separate v and mv variables.

The weights in the two files have already been normalized to have a mean of 1 (1,000,000 with the usual factor). If you combine the files as described, the number of cases in the two files will differ, and that will accurately convey the different numbers of men and women in the household population, as identified in the PR files. The weights in the IR and MR files have also already been adjusted for any nonresponse (loss of cases when going from the PR file to the IR and MR files). For svy purposes you don't need to change the cluster or strata ID codes. So it's much simpler than pooling surveys from different countries or time periods.
Re: Guidance regarding Gender Pooling in Liberia 2013 DHS data [message #19994 is a reply to message #19993] Fri, 11 September 2020 20:46 Go to previous messageGo to next message
Miatta is currently offline  Miatta
Messages: 3
Registered: September 2020
Member
Thank you so much. This is quite helpful. What is the best way to link the men and women dataset in Liberia With the HIV results info? I saw that the PR file has the HIV info but it seem as though the researcher has to use the household data to link the HIV info. Can you potentially suggest the best way to link the HIV results with the women and men? I saw that the barcode is the connecting the variable but only to the household dataset.
Thank you again for your guidance.
Re: Guidance regarding Gender Pooling in Liberia 2013 DHS data [message #20009 is a reply to message #19994] Tue, 15 September 2020 07:23 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2034
Registered: February 2013
Senior Member

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

The following lines will do what you want. It is not necessary to merge first with the PR file. You can merge directly with the IR+MR appended file.


* Stata code to merge AR with IR+MR, Liberia LB6A


* Prepare AR for merge
use e:\DHS\DHS_data\AR_files\LBAR6AFL.dta, clear
rename hivclust v001
rename hivnumb v002
rename hivline v003

sort v001 v002 v003

save e:\DHS\DHS_data\scratch\LBARtemp.dta, replace


* Prepare MR for append
use "C:\Users\26216\ICF\Analysis - Shared Resources\Data\DHSdata\LBMR6AFL.DTA", clear

* reduce the MR file to needed variables
keep mv0*
gen sex=1

* rename the mv variables
rename mv* v*

save e:\DHS\DHS_data\scratch\LBMRtemp.dta, replace


* Prepare IR

use "C:\Users\26216\ICF\Analysis - Shared Resources\Data\DHSdata\LBIR6AFL.DTA", clear

* reduce the IR file to needed variables
keep v0*
gen sex=2

append using e:\DHS\DHS_data\scratch\LBMRtemp.dta
label define sex 1 "man" 2 "woman"
label values sex sex

* Merge appended file with AR

sort v001 v002 v003
merge v001 v002 v003 using e:\DHS\DHS_data\scratch\LBARtemp.dta
tab _merge


After you have mv variables in the MR file to v variables, appended the IR and MR files
Re: Guidance regarding Gender Pooling in Liberia 2013 DHS data [message #20012 is a reply to message #20009] Tue, 15 September 2020 11:49 Go to previous message
Miatta is currently offline  Miatta
Messages: 3
Registered: September 2020
Member
Thank you so very much.
Previous Topic: Household crowding
Next Topic: Community level variable
Goto Forum:
  


Current Time: Sat Dec 5 00:54:29 Coordinated Universal Time 2020