The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » Ethiopia » Replicate Weighted/Unweighted Number of Children
Replicate Weighted/Unweighted Number of Children [message #14858] Wed, 09 May 2018 11:16 Go to next message
Messages: 2
Registered: May 2018
Location: Washington D.C.
Dear DHS Experts,

I am trying to replicate the numbers from Table 11.1 Nutritional Status of Children (Page 159), in Ethiopia 2011 report. Below is my code for getting the percentages for different age groups and the weighted and unweighted number of children:


gen stratid = v022
gen psu = v021
gen weight = v005/1000000
svyset psu [pw=weight], strata(stratid)

*living with mother (respondents)
keep if b9==0
*child's age in months
gen age=v008-b3
label var age "Age in Months"
*drop if not alive
keep if b5==1
*age intervals
recode age (0/5=1 "0-5")(6/8=2 "6-8")(9/23=3 "9-23")(24/59=4 "24-59")(else=.), gen(child_age)
*tab of all living children
tab child_age
tab child_age [iweight=weight]

*Stunted & Wasted
*The measures are presented with two implied decimal places.
*No decimal points are included in the data file.
*Stunted (Height/Age)
tab hw70, missing
gen stunted=0
replace stunted=1 if hw70<-200
replace stunted=. if hw70==.
replace stunted=. if hw70>600
tab stunted, missing
tab stunted [iweight=weight]
tab child_age stunted, row
tab child_age stunted [iweight=weight], row

My age intervals are slightly different from the report. But for example, the first category, children under 6 months, the numbers I got are still different from the report.

Percentage below -2SD: 9.92% (10.0% in the report); Weighted number of children: 1,042 (1,078 in the report); Unweighted: 995 (1015 in the report).

It would be really great if anybody could help me with this. Thanks in advance!

Yue Chen
Re: Replicate Weighted/Unweighted Number of Children [message #14885 is a reply to message #14858] Fri, 11 May 2018 11:10 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3114
Registered: February 2013
Senior Member

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

This table is constructed from the PR file, using hc70, and is limited to de facto children (hv103=1). The following lines will match the relevant numbers in the "total" row of the table:

gen stunted=0
replace stunted=1 if hc70<-200
replace stunted=. if hc70<-600 | hc70>600
summarize stunted [iweight=hv005/1000000] if hv103==1
Previous Topic: Calculating Timing of First PNC check up from EDHS 2011
Next Topic: Stillbirths from Ethiopia DHS 2016
Goto Forum:

Current Time: Wed Jul 17 15:36:08 Coordinated Universal Time 2024