[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: model fit in clogit
No doubt I'll get jumped on for being too simplistic, but I would simply
use tables indicating conventional levels of statistical significance in
order to assess the probability of obtaining a chi-squared value
(depending, as it does, on the degrees of freedom in your model).
In a response to one of my recent posts, Richard Williams alerted me to a
rather useful user-written post-estimation test called -tablesq-. I think
I'm right in saying that it comes as part of the StataQuest package.
Unfortunately, I've forgotten the search route that took me to it, but
-findit tablesq- ought to do it.
> I have a balanced panel of firms and times and three other explanatory
> variables. Given the binary nature of my explanatory variable I am running
> conditional (fixed effect) model with clogit specified as follows:
> xi: clogit y1 x1-xk i.t, group(firm)
> STATA gives me a Prob > chi2 = 0.1720 for LR chi2. Does this mean that the
> of my model is not good? How do I assess the goodness of fit of the model?
> many thanks
> Grazia Santangelo, PhD
> FacoltÓ di Scienze Politiche
> UniversitÓ degli Studi di Catania
> Via Vitt. Emanuele, 8
> 95131 Catania
> UniversitÓ di Catania - C.E.A.
> Servizio di Posta Elettronica
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
CLIVE NICHOLAS |t: 0(44)191 222 5969
Politics Building |e: email@example.com
School of Geography, |f: 0(44)870 126 2421
Politics & Sociology |
University of |
NE1 7RU |
United Kingdom |http://www.ncl.ac.uk/geps
* For searches and help try: