The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Dataset use in Stata » Food security measurement from Nepal DHS2011
Re: Food security measurement from Nepal DHS2016 [message #13908 is a reply to message #13882] Tue, 23 January 2018 12:30 Go to previous messageGo to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3214
Registered: February 2013
Senior Member
Please see the following response from DHS Technical Specialist, Rukundo Benedict:

Your subject line refers to the Nepal 2011 survey but the question is about the Nepal 2016 survey. We have looked at the archived CSPro code that was used to produce the tables in the main report on the 2016 survey. It appears that there was an error in the coding of the "Household Food Insecurity Access Scale Indicator Guide". The problem is that the code used in the report does not specify how to use sh145b=1. This is "unable to eat preferred foods because of lack of resources", response "rarely". Apparently this response should indicate "mild food insecurity".

I will paste below the Stata code that should be correct, but will not match the report. I have highlighted in yellow the piece that was missing (missing from the CSPro version). Please check. If you drop the yellow piece I believe you will get a match with the report. If you include it you will not get a match but will get the correct values.

We will discuss whether to issue an erratum. We will also check whether this error occurred in any other survey reports. Thanks for identifying the problem.


gen foodsec=.

replace foodsec=1 if (sh145a==0 |sh145a==1) & sh145b==0 & sh145c==0 & sh145d==0 & sh145e==0 & sh145f==0 & sh145g==0 & sh145h==0 & sh145i==0  

replace foodsec=2 if sh145a==2 |sh145a==3 | sh145b==1 | sh145b==2 | sh145b==3 | sh145c==1 | sh145d==1 & ( sh145e==0 & sh145f==0 & sh145g==0 & sh145h==0 & sh145i==0) 

replace foodsec=3 if sh145c==2 | sh145c==3 | sh145d==2 | sh145d==3 | sh145e==1 | sh145e==2 | sh145f==1 | sh145f==2 & (sh145g==0 & sh145h==0 & sh145i==0)

replace foodsec=4 if sh145e==3 | sh145f==3 | sh145g==1 | sh145g==2 | sh145g==3 |sh145h==1 | sh145h==2 | sh145h==3 | sh145i==1 | sh145i==2 | sh145i==3  

label define foodsec 1"Food secure" 2 "Mildy food insecure" 3 "Moderately food insecure"  4 "Severely food insecure"
label val foodsec foodsec
label variable foodsec "Household Food Insecurity Access Category"
 
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Previous Topic: How to carry out Individual Meta-analysis of DH surveys in sub-Saharan Africa using Stata
Next Topic: Cluster level population density data (Geospatial Covariate Datasets)
Goto Forum:
  


Current Time: Wed Dec 18 13:02:19 Coordinated Universal Time 2024