The DHS Program User Forum: India » Discrepancy in Estimates using NFHS5

Home » Countries » India » Discrepancy in Estimates using NFHS5

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

Discrepancy in Estimates using NFHS5 [message #24624]

Thu, 09 June 2022 07:10

aarushikataria
Messages: 1
Registered: June 2022

Member

Hello,

I was trying to obtain an estimate of the proportion of women that consume alcohol using the NFHS5 Individual Recode. The below is the code I was running on STATA:
sampleweight = v005/1000000
rename (s720 s721) (wifealc wdrinkfreq)
egen strata = group(v024 v025), label
* tab strata
svyset [pweight=sampleweight], psu(v021) strata(strata)
svy: tab wifealc

This gives me that 0.74% of women consume alcohol. However, the DHS and NFHS5 report say this number is 1.3%. On closer inspection, I found that the DHS report (https://www.dhsprogram.com/pubs/pdf/FR375/FR375.pdf) notes that the total number of observations in this dataset are 1,044,919 to arrive at 1.3%. However, the Individual recode has only 724,115 observations. Could the difference in observations be the reason for discrepancy?

Would be very grateful for any leads.

Report message to a moderator

[Message index]

Discrepancy in Estimates using NFHS5

By: aarushikataria on Thu, 09 June 2022 07:10

Previous Topic:	Individual Recode Data
Next Topic:	Caste waves 2015-2019

Goto Forum:

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Mon Nov 25 06:01:37 Coordinated Universal Time 2024