| Re: Merging child's malaria results from HH member recode dataset with other child data in Child recode [message #2926 is a reply to message #2905] |
Fri, 12 September 2014 06:11   |
kate2
Messages: 15
Registered: May 2014
|
Member |
|
|
Hello again,
Could you advise me on why I might have lost cases during my merge of datasets.
I merged the household member recode (PR) to the child recode (KR) using the chid recode as the active dataset and the HH member recode as the file to merge onto it.
I matched these as we discussed below.
You mentioned that the PR dataset may well include data for children who not appear in the KR dataset (as in the PR data on all children in the household were collected through the household questionnaire, whereas the KR dataset comprise data on children of the eligible women responding to the individual questionnaire). I assume that the way I have done the merge means that I will retain all cases from the KR dataset and merge additional variables available for these children from the PR dataset. I specified that cases should not be added and therefore any information on children which are included in the PR but not the KR will not be in my final dataset. I don't appear to have additional cases so I think I have achieved what I wanted.
However the original KR file has 8648 cases whereas my merged file has 8573 cases. What could be the reason for cases being lost from the file?
Thank you for your help
Kate
|
|
|
|
The DHS Program User Forum
Members
Search
Help
Register
Login
Home
