Maarten, Richard, Dimitri:
Thanks a lot,
effect coding was exactly what I was looking for.
Spared me days of frustation...
Silke
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Silke Humbert
Sent: Dienstag, 15. August 2006 22:14
To: [email protected]
Subject: st: contrast with probit
Dear Stata-community,
I would be happy if someone could help me with the following
problem:
I am using probit with linearly dependent explanatory variables
(i. e. age categories 0-30, 30-50, >50, coded 0,1). If am doing
the regression with all these explanatory variables Stata
naturally drops one if these variables.
The problem now is that I don't want the coefficients of the
regression relative to the variable dropped but rather to the total
average.
And in this way, I would like to have coefficients to all of my
variables (they should sum up to zero then, I think), even though
they are linearly dependent.
Is there a way to set contrasts with probit or any transformation I
can use (if it is a transformation how do I transform a missing
coefficient (dropped category)?)
I am using Stata 8.
Thanks a lot for any comments!
Silke
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
