Dear Eva and Kit,
Indeed my Governorate variable had differnt values in each dataset. I have corrected them and it seems Ok now.
Indeed if I would have looked carfully at the _merge variable I wouldn't have spent hours figuring out what was the problem.
I have typed: merge Governorate using dataset2, nokeep
thanks,
Gaby
--- On Mon, 5/11/09, Kit Baum <[email protected]> wrote:
> From: Kit Baum <[email protected]>
> Subject: re: st: problems with joinby or merge
> To: [email protected]
> Date: Monday, May 11, 2009, 11:15 AM
> <>
> Lots of MISSING VALUES FOR several of the individulas.
> Can someone let me know what Im doing wrong? How can I add
> variables for each of the individuals?
>
>
> Look at the data on your merge variable, Governorate, In
> the indiv dataset it ranges from 1-18. In the area dataset
> it ranges from 11-35. Obviously with a merge all those
> individuals with 1-10 values will not be matched. You should
> ALWAYS examine the _merge variable after a merge and think
> about what it is telling you. In this case it would identify
> cases = 1 (only in indiv dataset) and cases = 2 (only in
> gov. dataset -- potentially not a problem if the individuals
> only come from part of the country) as well as cases = 3
> (merged).
>
> The fact that there are 18 distinct values of Governorate
> in the area file suggests that you might need to recode the
> values in the indiv. dataset.
>
> Kit Baum | Boston College
> Economics & DIW
> Berlin | http://ideas.repec.org/e/pba1.html
>
> An
> Introduction to Stata Programming
> | http://www.stata-press.com/books/isp.html
> An Introduction to Modern Econometrics
> Using Stata | http://www.stata-press.com/books/imeus.html
>
>
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
