Re: [Gretl-devel] ordered logit/probit
On Mon, 14 Sep 2009, Allin Cottrell wrote:
(a) The count of "cases correctly predicted" (printed
beneath the
model) was not done in the standard manner, where predicted y is
the response-value with the greatest estimated probability.
Just in case Jack Lucchetti is reading this (Jack wrote the
original ordered logit/probit code) let me say that the "count of
correct cases" bug was almost certainly my fault. I suspect it
dates back to a change I made in gretl 1.7.7 (see
http://gretl.sourceforge.net/Backward.html , the entry for
8/28/2008). Sorry!
Allin Cottrell