You need to include both dummy variables in a single equation.
Peter
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of [email protected]
Sent: Friday, December 23, 2005 8:21 AM
To: [email protected]
Subject: st: regression coefficients
Dear Statalisters,
I have a peculiar question on regression models. I feel
like I know the answer, but can't quite get my brain around it.
I'm running two regression models on a data consisting of hormone
measurements on pregnant women measured at 3 points in time. The women are
divided into three mutually exclusive groups: normal, preterm birth outcome
(ptb) and infection. I made two dummy variables: hvptb: which would be 0 if
normal women and 1 if ptb, and hvinf: which would be 0 if normal women and 1
if the women had infection problems. My first regression model is
Log(crh)= b0 + b1*time + b2*hvptb + b3*(time*hvptb).