The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » Nepal » Correct numbers for merging the household and individual files of the 2001 DHS Nepal
Correct numbers for merging the household and individual files of the 2001 DHS Nepal [message #3573] Mon, 12 January 2015 20:15 Go to next message
UAB_user is currently offline  UAB_user
Messages: 21
Registered: September 2014
Location: Alabama
Member
Hello,

I was wondering if I could check to make sure my merging is done correctly. I am using the Nepal DHS and I am merging the household and individual files of the 2001 DHS. There are 8602 observations in the 2001 household data and 8726 observations in the individual files. When I merge them together I get 10251 observations. Is this correct? I always thought there was a 1:1 merge for the individual and household files?

Thank you
Re: Correct numbers for merging the household and individual files of the 2001 DHS Nepal [message #3911 is a reply to message #3573] Wed, 04 March 2015 15:18 Go to previous message
Liz-DHS
Messages: 1414
Registered: February 2013
Senior Member
Dear User,
Here is a response from one of our experts, Mr. Noureddine Abderrahim:
Quote:
Merging Household and individual data are based on matching the identifiers of these two types of data files namely the cluster number (HV001 for the household and V001 for the individual woman or MV001 for the individual men) and the household number ( HV002 for the household, V002 for women, and MV002 for men). In some instances these two variables (cluster number and household number) are not enough to identify the household. In this case using the first 12 characters of the individual identification (CASEID for women or MCASEID for men) would solve the problem. The number of cases will depend on how many individuals would match if you are matching individuals with their corresponding household but no more than the total number of individuals. In case you are matching households with the individual files, this case could lead to a result different from what you are expecting. In case you are merging the person's file with individual data files, the difference between the number of individuals and the persons will be those individuals who don't have a corresponding record in the individual file but the number of records will be no more than the total number of persons in the household.
Previous Topic: Merging Household+Female+Male files
Next Topic: Nutritional status of Children - Nepal (total sample size)
Goto Forum:
  


Current Time: Sun Dec 15 09:17:01 Eastern Standard Time 2019