The DHS Program User Forum: Dataset use in Stata

Home » Data » Dataset use in Stata » Hypertension in Nepal

Show: Today's Messages :: Show Polls :: Message Navigator

Hypertension in Nepal [message #13840]

Thu, 11 January 2018 02:53

Santosh
Messages: 8
Registered: January 2018
Location: Tokyo, Japan

Member

Hi,

I am trying to estimate the prevalence of hypertension among men and women using Nepal 2016 DHS data in Stata. The prevalence that I estimated is almost closer to the prevalence reported in Table 14.3.1 & 14.3.2.
However, the sample size doesn't match with the report.

I have attached the do file. I will be grateful if Experts form DHS could help me to match the exact sample size.

Thank you.

Regards,
Santosh

Attachment: sam dhs forum.do
(Size: 1.18KB, Downloaded 769 times)

Report message to a moderator

Re: Hypertension in Nepal [message #13847 is a reply to message #13840]

Thu, 11 January 2018 17:54

Bridgette-DHS
Messages: 3203
Registered: February 2013

Senior Member

Following is a response from Senior DHS Stata Specialist, Tom Pullum:

Your do file is well written. I think you only need to make two changes. First, the weight variable should be hv005, for both women and men. Second, you should restrict to de facto residents, i.e. the cases with hv103=1. With those changes, I get a match with the tables in the report.

Report message to a moderator

Re: Hypertension in Nepal [message #13859 is a reply to message #13847]

Sun, 14 January 2018 20:22

Santosh
Messages: 8
Registered: January 2018
Location: Tokyo, Japan

Member

Dear Madam/Sir,

Thank you for your support. I am able to match the sample size.

Regards,
Santosh

Report message to a moderator

Re: Hypertension in Nepal [message #14667 is a reply to message #13840]

Thu, 26 April 2018 14:15

Gowokani
Messages: 9
Registered: October 2016
Location: Malawi

Member

just a quick question, I am new to these things so i would want to learn alot

1. why do we have shbpsw and shbpsm ; shbpdw and shbpdm as seperat when for each variable they capture same info i.e shbpsw and shbpsm

2. How can I link back this new hypertension variable to individual recode in order to add a variable that is not in PR recod?

Thanks

Gowo

Gowokani Chijere Chirwa

Report message to a moderator

Re: Hypertension in Nepal [message #14672 is a reply to message #14667]

Fri, 27 April 2018 10:23

Bridgette-DHS
Messages: 3203
Registered: February 2013

Senior Member

Following is a response from Senior DHS Stata Specialist, Tom Pullum:

The fifth character in the variable name is s for systolic blood pressure and d for diastolic. The sixth character is w for women and m for men. It would have been possible to combine the w and m variables, because they refer to different cases, but DHS recode files often have this kind of separation for different subpopulations. For example, in the PR file, hc53, ha53, and hb53 are the hemoglobin concentrations for children, women, and men, respectively. If you would prefer to consolidate them into a single variable, that's easy to do.

Sometimes such variables are automatically put onto the relevant file. For example, ha53 is copied onto the IR file as v453 during construction of the IR file. However, I checked and it appears that shbpsw and shbpdw were not put into the IR file for this survey (NPIR7H). You will have to merge the PR and IR files, matching the id codes hv001, hv002, hvidx in the PR file with v001, v002, v003 in the IR file. Examples of how to do that are available elsewhere on the forum.

Report message to a moderator

Previous Topic:	problem with calculating the Alkire Foster multidimensional poverty index
Next Topic:	merging wealth index from Ethiopia DHS 2000 to women's file

Goto Forum:

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Wed Dec 4 00:18:03 Coordinated Universal Time 2024