The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Malaria » How to create composite variables (Comparison of trends between DHS 2015 and DHS 2022)
How to create composite variables [message #28823] Fri, 15 March 2024 01:45 Go to next message
nyamukondiwamel@gmail.com is currently offline  nyamukondiwamel@gmail.com
Messages: 5
Registered: January 2024
Member
I would like to create 1 variable from hml35_a to hml35_z so that i am able to compare the frequencies in malaria and also to determine if there are any associations with fever and residential place, age, KAP etc

I also tried using sb115_01 to sb115_13 but i still can not make the single variable. The results from 01 to 56 represent all the results or a single person is designanted to 01,02 ....56 per household?

[Updated on: Fri, 15 March 2024 02:45]

Report message to a moderator

Re: How to create composite variables [message #28876 is a reply to message #28823] Thu, 21 March 2024 08:56 Go to previous messageGo to next message
Janet-DHS is currently offline  Janet-DHS
Messages: 685
Registered: April 2022
Senior Member
Thank you for submitting your question. Could you please provide some more detailed information so we can better advise you?

Can you let us know:
• Which survey you are using (Include country name and year)?
• Which data files you are referring to?
• Which software you are using (Stata, SPSS, R, etc.)?

If you are trying to match a Table in a final report, please also indicate which table and which estimate you are trying to match.
Re: How to create composite variables [message #28882 is a reply to message #28876] Fri, 22 March 2024 00:18 Go to previous messageGo to next message
nyamukondiwamel@gmail.com is currently offline  nyamukondiwamel@gmail.com
Messages: 5
Registered: January 2024
Member
I am using Tanzania DHS 2015/16 and DHS 2022 and STATA for analysis. I want to use the malaria result for children under five and there are many variables with malaria result. Which variable is for malaria result in children and also which questionnaire has the question for malaria result as i am failing to identify it. the variables for malaria results are hml32_01 to hml32_40 ,hml35_01 to hml35_56 and sb115_01 to sb115_13. i am getting confused on which result i can use for malaria in children and malaria in pregnant women/women. Thank you
Re: How to create composite variables [message #28889 is a reply to message #28882] Fri, 22 March 2024 16:06 Go to previous message
Janet-DHS is currently offline  Janet-DHS
Messages: 685
Registered: April 2022
Senior Member
Following is a response from DHS staff member, Tom Pullum:

It appears that you are using the HR file, which has one record for each household, rather than the PR file, which has one record for each person in the household. The subscripts _01, _02, etc., are the line numbers of individuals in the household, and if you switch to the PR file the line number is given with a separate variable, hvidx. I recommend using the PR file.

In the PR file for the 2022 survey, TZPR82 FL.dta, hml32 is the result of the malaria rapid test for each person. hml35 is in the data but in this survey it was not actually used. It is NA (coded with a dot) for each case. The other variable you mention, sb115, is not in the data at all.

In the PR file for the 2015-16 survey, TZPR7BFL.dta, hml32 is the result of the smear test and hml35 is the result of the rapid test. sb115 is also the result of the rapid test. I recommend that you ignore sb115. It simply duplicates hml35 but is reverse coded and does not apply to as many cases (see below). Let us know if you have other questions.

. correlate hml35 sb115

(obs=9,322)

 
             |    hml35    sb115
-------------+------------------
       hml35 |   1.0000
       sb115 |  -1.0000   1.0000

 
. tab hml35 sb115,m

 
result of |

   malaria |           result for malaria rdt

rapid test |  positive   negative      other          . |     Total
-----------+--------------------------------------------+----------
  negative |         0      8,206          0      1,348 |     9,554
  positive |     1,116          0          0        265 |     1,381
         . |         0          0          3     53,942 |    53,945
-----------+--------------------------------------------+----------
     Total |     1,116      8,206          3     55,555 |    64,880

Previous Topic: Bednet coverage estimation issues
Goto Forum:
  


Current Time: Sat Apr 13 08:00:16 Coordinated Universal Time 2024