Burkina Faso 2010 DHS Report [message #14674] |
Fri, 27 April 2018 10:50 ![Go to next message Go to next message](/theme/default/images/down.png) |
rhuang
Messages: 12 Registered: April 2017
|
Member |
|
|
I am trying to re-create the table from the Burkina Faso 2010 DHS Report concerning the nutritional status of children. I am looking specifically at Tableau 11.12 (page 187). I am wondering which data set was used to generate this table? Was it the KR (children's recode) file or the PR (individual household member recode) file? I cannot seem to get the total number of children in the report to match with what I have generated (total number of children in report=6,994)
Can someone give me some direction on which data file and which variable was used to generate these height-for-age standard deviation cutoffs (<-2 s.d. and <-3 s.d.)?
Thanks,
Rachel
|
|
|
|
|
|
|
Re: Burkina Faso 2010 DHS Report [message #14712 is a reply to message #14691] |
Tue, 01 May 2018 14:20 ![Go to previous message Go to previous message](/theme/default/images/up.png) ![Go to next message Go to next message](/theme/default/images/down.png) |
rhuang
Messages: 12 Registered: April 2017
|
Member |
|
|
I cannot seem to obtain that number of 6,994 children from the Burkina Faso 2010 DHS report from the PR data file that have height-for-age and weight-for-age z-score data. In the PR data file, I see that there are 7,315 children with non-missing data. When I remove the observations that have: height out of plausible limits, age in days out of plausible limits, flagged cases, and observations=9999, I see that the total number of children with height-for-age and weight-for-age z-scores is 6,883. Even when I run a simple tabulation with the household weight variable in STATA, I do not get 6,994 children which is what is reported in the DHS report. Am I missing something?
-Rachel
|
|
|
Re: Burkina Faso 2010 DHS Report [message #14956 is a reply to message #14712] |
Mon, 21 May 2018 08:51 ![Go to previous message Go to previous message](/theme/default/images/up.png) |
Bridgette-DHS
Messages: 3139 Registered: February 2013
|
Senior Member |
|
|
Following is a response from Senior DHS Stata Specialist, Tom Pullum:
The 6994 is the weighted number of de facto children who have valid scores on hc70. The follow lines will give what you want.
gen stunted=0
replace stunted=1 if hc70<-200
replace stunted=. if hc70<-600 | hc70>600
tab stunted [iweight=hv005/1000000] if hv103==1
|
|
|