The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » Bangladesh » Number of respondents mismatch in dataset and published report
Number of respondents mismatch in dataset and published report [message #9665] Mon, 02 May 2016 02:35 Go to next message
gkibria1@jhu.edu is currently offline  gkibria1@jhu.edu
Messages: 1
Registered: May 2016
Location: Baltimore, MD, USA
Member
Hi
I was using the dataset of DHS 2014 of Bangladesh for a paper in my university. I already took permission of that. I was looking also at the published Bangladesh Demographic and Health Survey 2014 by the USAID. Wne I looked into the table 7.2 (page number 75) of the published report/book, I found that the number of respondents living in urban area was 4,709 and 12,149 in rural area. But when I was analyzing the dataset (in stata) BDIR70FL.DTA, I found the number was mismatch (6,1666 in urban and 11,693 in rural). Can you please help me to explain this?
Regards,
Kibria
Re: Number of respondents mismatch in dataset and published report [message #9684 is a reply to message #9665] Fri, 06 May 2016 11:03 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3208
Registered: February 2013
Senior Member
Following is a response from Senior DHS Stata Specialist, Tom Pullum:


Two problems. First, you are not using weights. Virtually every number in DHS tables is weighted. Second, you are not using marital status. The table is restricted to currently married women. It is important to read the table titles carefully. If you run this line, "tab v501 v025 [iweight=v005/1000000]" in that file, the top line (rounded to the nearest integers) will give 4709 and 12149.
Re: Number of respondents mismatch in dataset and published report [message #12423 is a reply to message #9684] Mon, 15 May 2017 00:19 Go to previous messageGo to next message
Soleil Von is currently offline  Soleil Von
Messages: 1
Registered: May 2017
Member
Hi,I also have the same question.I am using Bangladesh DHS survey in 2014 for one of my projects. I am using Individual Record(BDIR70DT). I am writing for difference between the results I summaried based on IR files and the DHS final reports.I will really appreciate your help in clarify my doubts.
There are 17863 women in IR files.The final report shows 5047 women of them live in urban area.(P29,table 3.1) However,I analysis there are 6167 urban women using R. The number of every residence is also different.
Now I know maybe I don't use weights to analysis,but I don't know what the weight is and how to use it.could you explain it for me?
Thank you very much for your time.
Best regards,
Soleilvon

Re: Number of respondents mismatch in dataset and published report [message #12425 is a reply to message #12423] Mon, 15 May 2017 11:22 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3208
Registered: February 2013
Senior Member

Following is a response from Senior DHS Stata Specialist, Tom Pullum and DHS Senior Research Associate, Shireen Assaf:

The difference between the 6167 and the 5047 is completely due to the use of weights. Below I will paste the results in Stata, first without weights and second with weights, using BDIR70FL.dta. I do this with iweight but you can also do it with pweight, svyset, and svy.

index.php?t=getfile&id=722&private=0

To produce the weighted table in R, you would need to use the survey package. The following lines should help you get started.

library(survey)
# install and load the survey package
options(survey.lonely.psu="adjust") 
# to fix the issue with strata with single PSU
# adjust will center the stratum at the population mean

data$wt = data$v005/1000000
# create the weight variable

mydesign<-svydesign(id=data$v021, data=data, strata=data$v023,  weight=data$wt, nest=T)
# set the survey design using the uploaded data (named data), the cluster (v021), the strata (v023) , and the weight (wt).
# then use svymean or svytable to get the weighted proportions and frequencies of your variables.  See the survey package documentation for further details. 



  • Attachment: tab-v025.jpg
    (Size: 28.26KB, Downloaded 740 times)

[Updated on: Mon, 15 May 2017 11:23]

Report message to a moderator

Previous Topic: Height and Weight
Next Topic: Mother's education
Goto Forum:
  


Current Time: Wed Dec 11 17:55:53 Coordinated Universal Time 2024