st: paired sample based on multiple characteristics

[Gokhan Yilmaz <statacurious@gmail.com>]

Dear All,

I have a dataset in which there are two groups of companies (described
with a variable that equals to 1 if the company is in group 1 and 2 if
in group 2). I want to create a paired sample of companies based on
let's say industry and size (nearest match), then it is easy and fair
to compare the average group stock returns between these two groups. I
made a lot of search and there are many commands (mostly used in
epidemiology research) but i did not come across one that exactly does
what i want. Can you recommend a command that can create a paired
sample of firms out of a single combined dataset where matching can be
done based on more than one characteristic?

Thank you,

Gokhan
*
*   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/