How the KR file is created [message #3068] |
Sat, 11 October 2014 08:54 ![Go to next message Go to next message](/theme/default/images/down.png) |
myat
Messages: 4 Registered: September 2014
|
Member |
|
|
Hi
I have a question about the KR file. Who are the children in the KR file? Are they all the children of the interviewed mothers (dead or alive)? Or are they all the children living in the house at the time of the interview? Do the file include only children under-5 or what is the age limit. I am trying to analyze the data with the under-5 child death as the outcome of interest, and not sure which file to use. The outcome of interest is "Any under-5 death in the family (irrespective of when it was occurred, and whether the child would be under-5 at the time of the survey if he/she would still be alive. Any advice or suggestion?
Myat
|
|
|
|
Re: How the KR file is created [message #3191 is a reply to message #3068] |
Tue, 04 November 2014 11:47 ![Go to previous message Go to previous message](/theme/default/images/up.png) ![Go to next message Go to next message](/theme/default/images/down.png) |
lucianabrondi
Messages: 18 Registered: October 2014 Location: Scotland
|
Member |
|
|
Dear colleagues,this is a basic question, but similar to the colleague: when I inspected the caseid variable ( Unique id for children) in the child recode file for Bangladesh(most recent), I found:
unique values: 7325 missing "": 0/8753
Do I have info on 8753 or 7325 children?
Luciana
myat wrote on Sat, 11 October 2014 13:54Hi
I have a question about the KR file. Who are the children in the KR file? Are they all the children of the interviewed mothers (dead or alive)? Or are they all the children living in the house at the time of the interview? Do the file include only children under-5 or what is the age limit. I am trying to analyze the data with the under-5 child death as the outcome of interest, and not sure which file to use. The outcome of interest is "Any under-5 death in the family (irrespective of when it was occurred, and whether the child would be under-5 at the time of the survey if he/she would still be alive. Any advice or suggestion?
Myat
Luciana Brondi
CPHS, University of Edinburgh
|
|
|
Re: How the KR file is created [message #3193 is a reply to message #3191] |
Tue, 04 November 2014 12:22 ![Go to previous message Go to previous message](/theme/default/images/up.png) ![Go to next message Go to next message](/theme/default/images/down.png) |
Liz-DHS
Messages: 1516 Registered: February 2013
|
Senior Member |
|
|
Dear Luciana,
I took a look at the documentation provided with the data files for Bangladesh DHS 2011. Here is an excerpt:
Quote: 8,753 children < 60 months (8, 789 weighted)
All the tables in our final reports show weighted numbers unless otherwise specified.
Hope this helps.
Thank you for your post.
|
|
|
Re: How the KR file is created [message #3195 is a reply to message #3193] |
Tue, 04 November 2014 12:44 ![Go to previous message Go to previous message](/theme/default/images/up.png) ![Go to next message Go to next message](/theme/default/images/down.png) |
lucianabrondi
Messages: 18 Registered: October 2014 Location: Scotland
|
Member |
|
|
Thanks, Liz, I was just wondering why the Stata program identified less children with unique caseid number than the total number of children, is it possible to have the same id number for 2 different children?
Luciana Brondi
CPHS, University of Edinburgh
|
|
|
Re: How the KR file is created [message #3218 is a reply to message #3191] |
Fri, 07 November 2014 21:31 ![Go to previous message Go to previous message](/theme/default/images/up.png) |
Trevor-DHS
Messages: 802 Registered: January 2013
|
Senior Member |
|
|
Caseid is not unique for children. It is unique for the women in the individual recode (IR) file, and each of the woman's children get the same case ID, and their own line number within the woman's case.
|
|
|