Statalist


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

Re: st: Note warning after discrete-time logit model


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Note warning after discrete-time logit model
Date   Wed, 29 Jul 2009 06:45:33 +0000 (GMT)

--- On Wed, 29/7/09, Lu, Zhenyan wrote:
> I have a question regarding the note warning after running
> discrete-time logit model.
> After the result table reported in Stata, sometimes there
> is note that says
> "Note: 61 failures and 0 successes completely determined."
> All others are regular.
> 
> I checked relevant Stata guidance that basically it says
> this may be caused by empty cells. So I deleted all empty
> cells and rerun models, but still with this kind of
> problem.

Empty cells means empty cells in a cross-tabulation of 
your dependent and independent variables not in your 
data-matrix. It could for instance occur when in a year 
there are no events.

For a more regular way of doing a discrete time survival 
analysis see:
http://www.iser.essex.ac.uk/iser/teaching/module-ec968 . 
I am actually not sure if this will solve your problem, 
but at least you will be able to present your results in 
a metric that is more common to survival analysis people 
(hazard ratios rather than odds ratios), which may make 
it easier to "sell" your paper.

Hope this helps,
Maarten

-----------------------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://home.fsw.vu.nl/m.buis/
-----------------------------------------


      

*
*   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   |   What's new   |   Site index