Hi statalist,

I'm trying to make a regressions analysis of variables X --> Y, I'm interested in the general relationsship but will also be looking at the relationsship over the years 1989-2014.

The X variable has been tracked in two different kinds of yearly surveys from 1989-1994 and from 2004-2014 and the Y variable from 1989-2014. With all of these I've taken the survey from one year, appended it with they survey from the second year and so forth, so now I have X tracked in two datasets, one from 1989-1994, one from 2004-2014 and X tracked in one dataset from 1989-2014.

My problem is how I should combine these three datasets in order to make the analysis, I've tried with append, but stata tells me that it doesn't have any observations, which I think is because the individual level observations doesn't have both the X and Y variable. I've also tried using 1:1 merge on my "year"-variable, but stata tells me that "year does not uniquely identify observations in the master data".

So my question is how I should combine the datasets to make the analysis possible.

Thanks in advance,
Kasper Lovén