The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Nutrition and Anthropometry » Missing values height information among women (Missing values height information among women)
Missing values height information among women [message #19025] Sun, 05 April 2020 14:28 Go to next message
ewa.b is currently offline  ewa.b
Messages: 33
Registered: January 2014
Member
I have a question about the missing information on the variable about women's height in the women's recode (variable v438). For example, in Uganda 2016 round, there is 66.72% of values missing. Variable v447 suggests that this information is missing because of "no measurement found in the household". Could you explain what that means? I went through the forum and the only explanation I found was regarding the missing information on height in children's recode and I cannot figure out why there would missingingess for women. This is especially as in the report for that country-round, it is mentioned that all women 15-49 were eligible to be measured and that for 98% of eligible women height information was collected. That is not in line with what is in the dataset.

I would be greateful for clarifying.
Thanks!
Ewa
Re: Missing values height information among women [message #19044 is a reply to message #19025] Tue, 07 April 2020 15:49 Go to previous message
ewa.b is currently offline  ewa.b
Messages: 33
Registered: January 2014
Member
I think in the meantime I found the answer to my question- in another part of the report I noticed a mention that only 1/3 of households were selected for anthropometry data collection. I have two additional questions regarding this issue:

1)Does "no measurement found in the household" in women's recode always mean that a given woman lived in a household that was not selected for anthropometry data collection? I conduct cross-country analysis so I would like to make sure that it is safe to assume that across surveys.

2)How should one apply sample weights when calculating measures of height using surveys for which only a subsample of the sample of women aged 15-49 was chosen for anthropometry data collection? Can one simply use v005? My worry is that this sample weight reflects the probability of a given woman being selected for the interview in general and not for the interview about anthropometry.

I would be grateful for your help.
Ewa
Previous Topic: Maternal anthropometry is calculated
Next Topic: Myanmar_Breastfeeding and Anthropometry data
Goto Forum:
  


Current Time: Wed May 12 11:06:38 Coordinated Universal Time 2021