The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Reproductive Health » Afghanistan DHS (about sample )
Afghanistan DHS [message #24491] Mon, 23 May 2022 19:19 Go to next message
Samishreyaan is currently offline  Samishreyaan
Messages: 6
Registered: May 2022
Member
I am working on teenage pregnancy project for Afghanistan, Bangladesh and many more. I need a sample for "all woman aged 15-19" instead of
"ever married woman aged 15-19". DHS for Afghanistan, Bangladesh and Pakistan collected the sample from ever married woman but the DHS report for teenage motherhood was presented for 'all woman'. Can you please assist me how do I increase it to all woman factor?
regards,
Sami
Re: Afghanistan DHS [message #24501 is a reply to message #24491] Tue, 24 May 2022 16:45 Go to previous messageGo to next message
Janet-DHS is currently offline  Janet-DHS
Messages: 658
Registered: April 2022
Senior Member
Following is response from DHS Research & Data Analysis Director, Tom Pullum:

The following lines should match the reports, where teenft is calculated as in your other forum question about Pakistan:

gen wt=v005/1000000
svyset [pw=wt], psu(v021) strata(v023) singleunit(centered)
gen awfact = awfactt/100
svy: ratio teenft/awfact

If you want to do this within subpopulations, you should use other versions of awfact, such as awfactr, that are in the data files and are described in the Guide to DHS Statistics.
Re: Afghanistan DHS [message #24510 is a reply to message #24501] Wed, 25 May 2022 07:59 Go to previous messageGo to next message
Samishreyaan is currently offline  Samishreyaan
Messages: 6
Registered: May 2022
Member
Hi Janet,
Thankyou for the post. When I used the command you gave, the sample (15-19 years) matches the report. However, when I cross tabulate the sample with teenage pregnancy the number doesn't match the report. To make teenage pregnancy variable, I used the following command in stata.

gen teenmom=0 if v013==1
replace teenmom=1 if (v213==1|bidx_01==1) & v013==1


Your help would be much appreciated.
kind regards,
SAMI
Re: Afghanistan DHS [message #24527 is a reply to message #24510] Thu, 26 May 2022 16:40 Go to previous messageGo to next message
Janet-DHS is currently offline  Janet-DHS
Messages: 658
Registered: April 2022
Senior Member
Following is response from DHS Research & Data Analysis Director, Tom Pullum:

Please be specific about which number in which table you are unable to match, and we will try to help.
Re: Afghanistan DHS [message #24530 is a reply to message #24527] Thu, 26 May 2022 19:38 Go to previous messageGo to next message
Samishreyaan is currently offline  Samishreyaan
Messages: 6
Registered: May 2022
Member
Hi Janet,
I am currently working on pooled analysis from Afghanistan, Pakistan, Bangladesh, Nepal, Maldives and India DHS to find risk factors of teenage pregnancy. What I can see the sample of women is 'all woman 15-49 yrs' for Nepal, India and Bangladesh; whereas the sample of woman
for Afghanistan, Pakistan and Bangladesh is "ever married woman 15-49 yrs". This is where I applied all woman factor to increase the sample of woman for those three countries. By doing so, I did get an exactly sample number of woman sample as reported in DHS report but, failed to get the correct percentage of woman who have begun childbearing. For example, lets take Afghanistan DHS. My analysis showed Percentage of childbearing is 59.5% whereas the report states 12.1%.
my work on stata and the DHS report snapshots are attached below.
I wish to get quicker response, as I am running out of my time.
kind regards,
SAMI/index.php?t=getfile&id=1851&private=0/index.php?t=getfile&id=1852&private=0/index.php?t=getfile&id=1853&private=0
  • Attachment: snip 1.PNG
    (Size: 10.38KB, Downloaded 421 times)
  • Attachment: snip 2.PNG
    (Size: 4.28KB, Downloaded 288 times)
  • Attachment: snip 3.PNG
    (Size: 31.28KB, Downloaded 427 times)
Re: Afghanistan DHS [message #24531 is a reply to message #24530] Fri, 27 May 2022 03:17 Go to previous messageGo to next message
schoumaker is currently offline  schoumaker
Messages: 65
Registered: May 2013
Location: Belgium
Senior Member
Hello,
This is due to the fact that you are weighting both the numerator and the denominator with awfactt.
You can try the syntax below.
Best,
Bruno


****

use AFIR71FL.DTA, clear
keep if v012>=15 & v012<=19
gene teenmom=0
replace teenmom=1 if v213==1|bidx_01==1
replace awfactt=awfactt/100
gene teenmom_prop=teenm/awfactt // divides each observation by the all-women factor
tabstat teenmom_prop [aw=v005*awfactt]


tabstat teenmom_prop [aw=v005*awfactt], by(v012) // by age


*** you will need to adapt the all women factor for comparisons by urban-rural, education etc.






Bruno Schoumaker
Centre for Demographic Research
Université catholique de Louvain
Re: Afghanistan DHS [message #24532 is a reply to message #24531] Fri, 27 May 2022 03:24 Go to previous messageGo to next message
schoumaker is currently offline  schoumaker
Messages: 65
Registered: May 2013
Location: Belgium
Senior Member
Hello again,
The syntax that Tom Pullum sent you a few days ago is better (and also provides confidence intervals).
Bruno

***

use AFIR71FL.DTA, clear
keep if v012>=15 & v012<=19
gene teenmom=0
replace teenmom=1 if v213==1|bidx_01==1

gen wt=v005/1000000
svyset [pw=wt], psu(v021) strata(v023) singleunit(centered)
gen awfact = awfactt/100
svy: ratio teenmom/awfact


Bruno Schoumaker
Centre for Demographic Research
Université catholique de Louvain
Re: Afghanistan DHS [message #24540 is a reply to message #24530] Fri, 27 May 2022 12:51 Go to previous message
Janet-DHS is currently offline  Janet-DHS
Messages: 658
Registered: April 2022
Senior Member
Following is response from DHS Research & Data Analysis Director, Tom Pullum:

If you open the AF file for women (the IR file) and then enter the following lines, you will get .1207. This is a proportion. Multiply it by 100 and then round to the nearest tenth of a percent and you get 12.1, which is the desired number.

gen teenmom=0 if v013==1
replace teenmom=1 if (v201>=1 | v213==1) & v013==1
svyset [pw=v005], psu(v021) strata(v023) singleunit(centered)
gen awfact = awfactt/100
svy: ratio teenmom/awfact
Previous Topic: Information on whether a birth was preterm ?
Next Topic: Indonesian DHS - Unintended pregnancy
Goto Forum:
  


Current Time: Thu Mar 28 11:17:57 Coordinated Universal Time 2024