Jay Verkuilen wrote:
Wasn't suggesting it for the mixed model, just that in a classic
clustering scenario like is here, using clustered resampling or
jackknifing is an alternative to the parametric assumptions on summary
measures. In a small sample mixed model case, I suspect that going to a
fully Bayesian model is the only way to go. Even then things may not
work so well.
I look forward to hearing the answer you and David come up with.
--------------------------------------------------------------------------------
Sorry, Jay, about my misreading. Resampling certainly is an alternative.
It would be interesting to see how the bootstrap compares in a study like
David's under those potential outcomes in which summary measures would not
be expected to fare so well, e.g., binomial expectations in the neighborhood
of 0 of 50 or 50 of 50.
I share your suspicions about mixed models in small samples, Messrs. Kenward
and Roger notwithstanding.
Joseph Coveney
*
* 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/