The DHS Program User Forum: Ethiopia » MDD and Sample size mismatch

Home » Countries » Ethiopia » MDD and Sample size mismatch

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

MDD and Sample size mismatch [message #22943]

Wed, 09 June 2021 09:17

Hassen
Messages: 121
Registered: April 2018
Location: Ethiopia,Africa

Senior Member

Dear DHS Experts, I used Ethiopia Mini-DHS 2019 ETKR81DT dataset for analysis and Stata 14/SE software. Using standardized Stata command from Github website from chapter 11 to match the result of Minimum Dietary Diversity in figure 9.5 (MDD=14%) and table 9.7 (MDD=14.4%) and also, the number of all children age 6-23 months was 1,463. The results of my analysis using Github Stata syntax for MDD and the results in figure 9.5 & table 9.7 were mismatch. So, I need your help please? Any Stata command to match the result?
Cheers, Hassen

Hassen Ali(Chief Public Health Professional Specialist)

Report message to a moderator

Re: MDD and Sample size mismatch [message #22953 is a reply to message #22943]

Thu, 10 June 2021 13:38

Shireen-DHS
Messages: 140
Registered: August 2020
Location: USA

Senior Member

Hello Hassen,

I was able to match the final report using the GitHub code. I think perhaps you didn't check the main file first (!NTmain.do). There are certain variables there you need to select the correct children. This was explained in the main do file. Mainly, before running the NT_IYCF.do file you need to run the following code (lines 62 to 101 in the main file) to select the correct children:

**** child's age ****
gen age = v008 - b3

* to check if survey has b19, which should be used instead to compute age.
scalar b19_included=1
capture confirm numeric variable b19, exact
if _rc>0 {
* b19 is not present
scalar b19_included=0
}
if _rc==0 {
* b19 is present; check for values
summarize b19
if r(sd)==0 | r(sd)==. {
scalar b19_included=0
}
}

if b19_included==1 {
drop age
gen age=b19
}

* Note: The following do files select for the youngest child under 2 years living with the mother. Therefore some cases will be dropped.
* Selecting for youngest child under 24 months and living with mother
keep if age < 24 & b9 == 0
* if caseid is the same as the prior case, then not the last born
keep if _n == 1 | caseid != caseid[_n-1]

Following this you can run the following to get the correct estimates for minimum dietary diversity as shown in Table 9.7:
gen wt=v005/1000000

*Among breastfeeding children
tab nt_mdd if nt_bf_curr==1 [iw=wt]
*gives 14.4 and 1246 children as in the report

*Among non-breastfeeding children
tab nt_mdd if nt_bf_curr==0 [iw=wt]
*gives 8% and 217 children as in the report

*Among all children
tab nt_mdd [iw=wt]
*gives 13.5 and 1463 children as in the report

Thank you.
Best,

Shireen Assaf
The DHS Program

Report message to a moderator

Re: MDD and Sample size mismatch [message #22960 is a reply to message #22953]

Fri, 11 June 2021 04:41

Hassen
Messages: 121
Registered: April 2018
Location: Ethiopia,Africa

Senior Member

Dear Shireen Assaf, Fantastic Your guidance is so helpful. Thank you!!

Sincerely yours, Hassen

Hassen Ali(Chief Public Health Professional Specialist)

Report message to a moderator

Re: MDD and Sample size mismatch [message #23832 is a reply to message #22953]

Sat, 11 December 2021 01:32

Sajhama
Messages: 28
Registered: July 2017

Member

Hi Shireen,

I could not find code for MDD for women (Table 11.13) code in Github. Please let me know asap.

Thank you
Sajama

Report message to a moderator

Re: MDD and Sample size mismatch [message #23836 is a reply to message #23832]

Mon, 13 December 2021 08:23

Shireen-DHS
Messages: 140
Registered: August 2020
Location: USA

Senior Member

Hello,

This indicator is not available in DHS data.

Thank you.
Best,
Shireen Assaf
The DHS Program

Report message to a moderator

Re: MDD and Sample size mismatch [message #23837 is a reply to message #23836]

Mon, 13 December 2021 08:46

Sajhama
Messages: 28
Registered: July 2017

Member

Dear Shireen,
Thank you for the reply.

I wanted to create Table 11.13. If the syntax is available please let me know.

Sajama

Report message to a moderator

Re: MDD and Sample size mismatch [message #23838 is a reply to message #23837]

Mon, 13 December 2021 08:55

Shireen-DHS
Messages: 140
Registered: August 2020
Location: USA

Senior Member

Please let us know which survey you are referring to. This thread was about the Ethiopia 2019 survey and there is no Table 11.13 for this survey.

Thank you.
Shireen

Report message to a moderator

Re: MDD and Sample size mismatch [message #23839 is a reply to message #23838]

Mon, 13 December 2021 08:58

Sajhama
Messages: 28
Registered: July 2017

Member

Nepal DHS 2016

Report message to a moderator

Re: MDD and Sample size mismatch [message #23840 is a reply to message #23839]

Mon, 13 December 2021 09:18

Shireen-DHS
Messages: 140
Registered: August 2020
Location: USA

Senior Member

Hello,

It appears this survey included a special module for this indicator. The DHS Program GitHub site only has code for indicators listed in the Guide to DHS Statistics.

For these indicators, you would need to use the IR file and check the variables on foods consumed by the mother (check des v47*). For instance for the tea indicator you would do the following:

gen age=b19_01
gen wt=v005/1000000
tab v471b if age<24 [iw=wt]

You may need to group some variables for to create the other food groups in the table. After you have coded each food group as described in footnote 2 of the table, then you would do the following:

* add the food groups
egen foodsum = rsum(group1 group2 group3 group4 group5 group6 group7 group8 group9 group10)
recode foodsum (1/4 .=0 "No") (5/10=1 "Yes"), gen(mdd)
replace mdd=. if age>=24

Thank you.
Best,
Shireen

Report message to a moderator

Previous Topic:	Child Poverty Analysis for Ethiopia
Next Topic:	Ethnicities 2019

Goto Forum:

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Sat Dec 21 07:11:40 Coordinated Universal Time 2024