You can also use xtile to get a new variable with quantile categories - quintiles are common. In one study I worked on the quintiles showed that the drugs administered didn't have much effect. Not only that, there was an effect only at the extremes of risk (either first of fifth quintile). I was surprised.
Tony
Peter A. Lachenbruch
Department of Public Health
Oregon State University
Corvallis, OR 97330
Phone: 541-737-3832
FAX: 541-737-4001
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Austin Nichols
Sent: Monday, February 01, 2010 9:18 AM
To: [email protected]
Subject: Re: st: RE: PSMATCH2 and panel data
See also
http://www.stata.com/statalist/archive/2009-12/msg00344.html
On Mon, Feb 1, 2010 at 5:45 AM, Nick Cox <[email protected]> wrote:
> I don't know, but it might be better to rephrase your question in terms
> of what you seek: Propensity scores that vary within panels as well as
> between? Is there any literature that does that?
>
> (Not my field at all, but I think this is a repeat of an unanswered
> question.)
>
> Nick
> [email protected]
>
> melia bruffman
>
> Does anyone knows if PSMATCH2 can be used with with panel data? thanks!
*
* 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/
