[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: Duration models: database preparation

From   Seema Bhatia <>
Subject   st: Re: Duration models: database preparation
Date   Mon, 1 Oct 2007 16:22:09 +0100

Dear Statalist

I am trying to compute Marginal Effects after an Ordered Probit Regression. 
While the underlying theory of it is clear, the intrpretation of the 
marginal effects, in partcular the signs on these are not clear to me.

In my model, I have negative, zero and positive growth of firms. e.g. one of 
the significant variables is market research. How do interpret the signs of 
the computed marginal effects in each of the categories? If anyone has come 
across any papers using this methodology and/or has examples of how to 
interpret the signs on the marginal effects I would be very grateful.

Many thanks

Seema Bhatia-Panthaki 

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index