Unique identifiers/duplicate entries in DHS Pakistan Data [message #3811] |
Mon, 16 February 2015 22:43 ![Go to next message Go to next message](/theme/default/images/down.png) |
nqayyum
Messages: 2 Registered: January 2015
|
Member |
![%40nainaqayyum](/theme/default/images/twitter.png)
|
|
Hi,
I am using the DHS Pakistan child recode data to make a panel dataset using STATA software. In the data however, there seem to be duplicate observations. I used the household, cluster and line number as the unique identifiers but even then there are some duplicate observations.
Is it possible that the same child from a household in a cluster may be interviewed twice at the same time and the information is included twice in the dataset as well?
I am having trouble figuring out why there will be duplicate entries for individuals in the dataset.
Thanks,
Naina
|
|
|
Re: Unique identifiers/duplicate entries in DHS Pakistan Data [message #3824 is a reply to message #3811] |
Wed, 18 February 2015 07:55 ![Go to previous message Go to previous message](/theme/default/images/up.png) |
Bridgette-DHS
Messages: 3151 Registered: February 2013
|
Senior Member |
|
|
Following is a response from Noureddine Abderrahim, Senior DHS Specialist:
You need to use the cluster number, the household number, the woman's line number, and the child's line number in the birth history (BIDX) to identify the child. This will ensure that you do not get duplicate cases as reported in your post.
Please keep in mind that some children do not live in the household, and for that reason, you can't use the line number in the household (B16).
|
|
|