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

st: RE: dropping outcomes in mlogit

From   "Verkuilen, Jay" <[email protected]>
To   <[email protected]>
Subject   st: RE: dropping outcomes in mlogit
Date   Thu, 3 Jan 2008 17:10:56 -0500

>>At a fist glance, there seem not to be excess of collinearity among
sectors and outcomes. How can I explain than one of the three outcomes
is dropped?<<

I would guess perfect prediction due to some combination of your
predictors. I'm surprised Stata didn't complain about it. You should
cross-tablulate your data to see where it might have fallen.


*   For searches and help try:

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