Merge m:1 using participant ID in matched case-control data - error messages

[Joe Tuckles]

Hi,

I have a matched case control dataset with 3 controls to every case. I have data that I want to merge into one dataset which is fine the first time I run the merge. But then attempting to merge a third file gives the output either:

variable _merge already defined
r(110);

If I input

drop _merge

I then get this output:

variable id does not uniquely identify observations in the using data

.

Can anyone advise?

Thanks

[Rich Goldstein]

your response to the first problem was correct

the second error message is telling you that your claim that each id only appears once in the "using" data is an incorrect claim - so you need to figure out why and fix it; you might start with

duplicates report id

to see how big a problem this is