The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Weighting data » Kenya DHS 2014; which sample weight to use?
Kenya DHS 2014; which sample weight to use? [message #12228] Thu, 13 April 2017 09:23 Go to next message
gatcho is currently offline  gatcho
Messages: 2
Registered: February 2017
Location: Marseille
Member
Hi all,
I am working on the determinants of the heath insurance ownership among the household head in kenya with the DHS dataset of kenya 2014 : KEHR70FL ; KEMR70FL ; KEIR70FL.
I am a beginner in stata and DHS data user
The unit of analysis is the household head.
I have merge these three datasets(KEHR70FL ; KEMR70FL ; KEIR70FL) because the question about health insurance ownership exist only in the man and woman database.
For the variable v481(covered by health insurance), there is 14636 household head with 3576 missing values.
My question :
1- What sample weight can i use to have representative result in national level?
Thanks.
Modeste


Modeste
Re: Kenya DHS 2014; which sample weight to use? [message #12230 is a reply to message #12228] Thu, 13 April 2017 11:18 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2536
Registered: February 2013
Senior Member
Following is a response from Senior DHS Stata Specialist, Tom Pullum:


I checked what you did with the Stata lines given below. I agree with what you got. I recommend that you construct a new weight that is v005 for the women and mv005 for the men. I call it v005_mv005 but you could call it whatever you want.

use e:\DHS\DHS_data\PR_files\KEPR70FL.dta, clear
keep hv001 hv002 hvidx hv005 hv101 hv104 hv105
keep if hv101==1
sort hv001 hv002 hvidx
save e:\DHS\DHS_data\scratch\PRtemp.dta, replace

use e:\DHS\DHS_data\IR_files\KEIR70FL.dta, clear
keep v001 v002 v003 v005 v481
rename v001 hv001
rename v002 hv002
rename v003 hvidx
tab v481,m

gen sex=2
save e:\DHS\DHS_data\scratch\IRtemp.dta, replace

use e:\DHS\DHS_data\MR_files\KEMR70FL.dta, clear
keep mv001 mv002 mv003 mv005 mv481
rename mv001 hv001
rename mv002 hv002
rename mv003 hvidx
tab mv481,m

rename mv481 v481
gen sex=1
save e:\DHS\DHS_data\scratch\MRtemp.dta, replace
append using e:\DHS\DHS_data\scratch\IRtemp.dta
sort hv001 hv002 hvidx

merge hv001 hv002 hvidx using e:\DHS\DHS_data\scratch\PRtemp.dta

tab _merge
keep if _merge==3
drop _merge
tab v481 sex,m

gen v005_mv005=.
replace v005_mv005==mv005 if sex==1
replace v005_mv005==v005 if sex==2
Re: Kenya DHS 2014; which sample weight to use? [message #12234 is a reply to message #12230] Fri, 14 April 2017 05:16 Go to previous messageGo to next message
gatcho is currently offline  gatcho
Messages: 2
Registered: February 2017
Location: Marseille
Member
Hi,
Thank you for your suggestion.

Just at the end of your code, it's work with one equal.
replace v005_mv005=mv005 if sex==1.
replace v005_mv005=v005 if sex==2

Thanks for the prompt response.



Modeste
Re: Kenya DHS 2014; which sample weight to use? [message #12237 is a reply to message #12234] Fri, 14 April 2017 07:47 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2536
Registered: February 2013
Senior Member
From Senior DHS Stata Specialist, Tom Pullum:


Thanks for fixing that! Tom
Previous Topic: Rwanda 2000 only 13 unique women's weights (v005)
Next Topic: Weights for Infant Mortality
Goto Forum:
  


Current Time: Thu May 19 20:36:40 Coordinated Universal Time 2022