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

st: probit convergence -- or not

From   [email protected]
To   [email protected]
Subject   st: probit convergence -- or not
Date   Thu, 24 Jan 2008 16:31:29 +0000

I'm running a probit on a set of many thousands of observations.
There are a few thousand variables involved, most of which are dummies hith very few 1s.
(I weeded out the constant-0 variables ahead of time.)

I know this is an awfully large set of variables; let's put that aside.

After 14 iterations, the log liklihood settled on a particular value (-8151.4912), and has been steady ever since. It has run for 18 hours and is up to 1160 iterations.

Will this ever end?
Does that fact that the log liklihood value has been steady for all but the first 14 iterations indicate that I am stuck in an endless loop?

Thanks if anyone can help.
*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index