| Merging IR and HIV data from Senegal 2005 [message #3149] |
Thu, 23 October 2014 05:17  |
hannekeyserhegdahl
Messages: 9
Registered: October 2014
|
Member |
|
|
Hi!
I am trying to merge individual and male recode with the data on hiv from Senegal 2005 in STATA. I have already appended the male and individual recode into one dataset and sorted on v001, v002 and v003, and given the same names to the variables in the hiv dataset.
When I try to merge the individual/male dataset with the hiv dataset 1:1, I get the message "variables v001 v002 v003 do not uniquely identify observations in the master data." I have done exactly the same for the Senegal 2010-11 dataset without any problems.
I have read somewhere that I may have more than one observation for one ID or something, so I tried to merge m:1, and then it worked (7717 were matched and 10753 were not matched). However, I do not understand what this means to my dataset. Can I use this as it is and be happy with only 7717 matched or is there another way of doing this so that I can get a match on every observation. When I have done this on other countries and also on the Senegal 2010-11 dataset, I was able to get a match on every observation.
Thank you in advance for any help.
Hanne
|
|
|
|
The DHS Program User Forum
Members
Search
Help
Register
Login
Home
