The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Service Provision Assessment (SPA) » SPA variables
SPA variables [message #23354] Thu, 26 August 2021 14:09 Go to next message
rhythm is currently offline  rhythm
Messages: 2
Registered: August 2021
Member
I would like to create some variables using SPA surveys.
*Malawi SPA 2013-14: X ray machine (table 3.7.1)
gen wt=facwt/1000000
gen xm=0
replace xm=1 if (q881a_1==1 & q881b_1==1) | (q881a_2==1 & q881b_2==1)
tab xm [iw=wt]
With this codes, the % is 6.97, but in the report the % is 5.
*Nepal SPA 2015: Full blood count with differentials (table 3.7.3)
gen wt=facwt/1000000
keep if factype==inrange(factype,1,7) | inrange(factype,12,14)
gen fblcn=0
replace fblcn=1 if ((q834==1 & q835==1) | (q802eb_1==1 & q802ec_1==1 & q802eb_2==1 & q802eb_3==1 & q802ec_3==1))
tab fblcn [iw=wt]
With this codes, the % is 73.52, but in the report the % is 66.9.
According to the footnotes, and questionnaire it looks like I am using right variables, but due to some reasons I am not getting the same % as the final report tables.
I would greatly appreciate any help with this matter.

Many thanks
Re: SPA variables [message #23368 is a reply to message #23354] Mon, 30 August 2021 08:24 Go to previous messageGo to next message
SaraDHS is currently offline  SaraDHS
Messages: 25
Registered: December 2020
Member
Dear rhythm,

For Malawi xray variable, in many countries, one of the criteria for the xray machine variable is that the facility uses xray for TB diagnosis as asked in q1903. If you are trying to calculate this variable for any country, please add that into your coding. If you do this for Malawi, you will get the same % as in the final report.

For Nepal, you are using incorrect variables for your definition of full blood count. Please doublecheck the footnotes in the table, which provide the definition used, as well as the questionnaire with the variables you used to define blood_count. If you recreate the definition with the correct variables, you will get a value within 1% of the final report.

Best,
Sara


Sara Riese, PhD Senior Demographic and Health Researcher, DHS Program
Re: SPA variables [message #23374 is a reply to message #23368] Tue, 31 August 2021 02:09 Go to previous messageGo to next message
rhythm is currently offline  rhythm
Messages: 2
Registered: August 2021
Member
Dear Sara,

Thanks a lot for your kindest support and I was able to create the variables.
I wanted to know, for the xray machine variable, the criteria that facility uses xray for TB diagnosis as asked in q1903, will I consider this for Tanzania?

Regards,
Rhythm
Re: SPA variables [message #23381 is a reply to message #23374] Tue, 31 August 2021 09:28 Go to previous message
SaraDHS is currently offline  SaraDHS
Messages: 25
Registered: December 2020
Member
Dear Rhythm,
The best way is to try both ways and see which matches the final report.

Best,
Sara


Sara Riese, PhD Senior Demographic and Health Researcher, DHS Program
Previous Topic: Creating two variable
Next Topic: About one SPA variable
Goto Forum:
  


Current Time: Sat Oct 16 17:44:32 Coordinated Universal Time 2021