Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: generating predicted probabilities, setting variables constant at mean or mode


From   Sara Head <sara.head@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: generating predicted probabilities, setting variables constant at mean or mode
Date   Mon, 29 Aug 2011 14:13:14 -0400

Hi Statalist,

I am graphing some predicted probabilities from a Generalized Ordered
Logistic Regression model. I am using Long & Freese's SPost commands
(i.e. prgen and praccum) and Williams' gologit2 (in Stata IC 11.2). My
model has both categorical and continuous predictors.

When I run praccum, I use the x() option to assign specific values to
some variables and then I use rest(mean) to set other variables
constant at their mean. Rest(mean) obviously makes sense for
continuous predictors, but it isn't intuitive for categorical
variables. I can't find SPost examples where, after specifying x(),
users set categorical predictors constant at their mode.

Could someone provide insight into why I would set categorical
predictors constant at their mean and not their mode?

Thanks,
Sara

*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index