Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Ordered Probit Interpretation
From
Richard Williams <[email protected]>
To
[email protected]
Subject
Re: st: Ordered Probit Interpretation
Date
Fri, 26 Aug 2011 11:15:33 -0500
At 08:55 AM 8/26/2011, Venkiteshwaran, Vinod wrote:
I am running an ordered probit model with pooled cross-sectional
data. The ordered dependent variable, Y_it has 7 categories that
sometimes change within each i. THe variable of interest is X_it. In
the results X_it enters the model with a highly significant negative
coefficient implying that the marginal effect of a change in X_it is
that it reduces(increases) the probability of the highest(lowest)
category of Y_it.
I then transformed the Y_it variable into changes and ranked the
changes, Y*_it. That is if the change is upward, downward or no
change, where the order is 3,2 and 1 respectively. I re-run my
ordered probit model with Y*_it as my dependent variable and the
same X_it. In this model X_it no longer has a significant
coefficient. Econometrically how should this insignificance be interpreted?
I am not sure why you are doing that, but in any event why would you
consider Y*_it ordinal? If you want it to be ordinal, I would think
you would want it to be upward, no change, downward. Or, use mprobit
rather than oprobit.
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* 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/