Re: st: comparing policies across countries: multilevel estimation?

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Thu, 16/12/10, Laura R. wrote:
> To be precise, with multilevel models I mean models that
> are based on individual data, but some individuals share
> some variables because they belong to the same kind of
> group. <snip> I thought maybe one has to treat them 
> differently than the other variables, as this is what
> multilevel models do, as far as I have heard. As to the
> selection, I would like to estimate the selection into
> employment and then the wages.

You are describing the aim, not how you want to do it. With
this type of modeling the devil is in the detail. For now
I would forget about selection, and first focuss on 
understanding the different forms of multilevel modeling 
and their advantages and disadvantages. A nice place to 
start would be: <http://www.stata.com/bookstore/mlmus.html>.
After that you can look if you still have time left to 
look at selection in a multilevel context.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   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/