RE: $OMEGA blocks and log-likelihood profiling
From: "Kowalski, Ken" Ken.Kowalski@pfizer.com
Subject: RE: [NMusers] $OMEGA blocks and log-likelihood profiling
Date: Wed, June 2, 2004 9:16 am
Nick, Nmusers,
Regardless of whether the $COV step fails, I have a hard time understanding
why only 28% of the bootstrap runs minimized successfully if it wasn't due
to over-parameterization. Note that over-parameterization does not mean
that the model is badly formed. It could indeed be a correctly specified
model (e.g., no lack of fit) just that the existing data do not support
estimating all of the parameters.
Ken