Hi Statalist,
This is probably very elementary. What's the usual test for testing if a
set of data fit a model?
Specifically if I have p_i, a set of probabilities, and y_i, a set of
binary observations, i = 1 to n; and I want to test whether y_i ~
bern(p_i) for all i.
I thought of calculating the expected and observed log-likelihood, and
then assume normality by the Central Limit Theorem, and testing using a
z-test. I think this is ok, but I need a reference in order to put this
in a paper. Or are there other more obvious tests with readily available
references?
Thanks,
Tim
*
* 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/
