Hello all,
I would like to test statistically for differences between the goodness of
fit of various parameterizations with stcox. In other words, I'd like to
find a way to test statistically for whether, by adding a given variable to
cox model A, the fit of the new model (call it B) is better than that of
the original model. I have multiple observations per respondent, and so
the usual tests - lrtest in particular - are not appripriate. I know that
I can use the aic option of -estimates table- to generate measures of the
goodness of fit of various model. But is there a way to test statistically
for differences in fit of different models?
Many thanks in advance for any advice that anyone might be able to provide.
Adam Thomas
John F. Kennedy School of Government
Harvard University
*
* 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/