RE: $OMEGA blocks and log-likelihood profiling

From: Nick Holford n.holford@auckland.ac.nz Subject: RE:[NMusers] $OMEGA blocks and log-likelihood profiling Date: Thu, June 10, 2004 3:55 pm Ken and Leonid, Thanks for all your thoughtful remarks and suggestions. I am afraid I am rather busy this week (leaving tomorrow for PAGE and 2 weeks in Europe) so I don't have time to take up the suggested investigations right now. But a quick thought -- Can either of you provide a data based example where you can show that bootstrap runs that minimized successfully with $COV produced more reliable parameter estimates than those that did not complete $COV or terminated? It seems that much of the discussion is based on opinion rather than data. I have offered some data to test the hypothesis that successful runs (+/- $COV) are better than all bootstrap runs. I realize it is only one data set (and I am working on another as I type) but it is data not just opinion. Nick -- Nick Holford, Dept Pharmacology & Clinical Pharmacology University of Auckland, 85 Park Rd, Private Bag 92019, Auckland, New Zealand email:n.holford@auckland.ac.nz tel:+64(9)373-7599x86730 fax:373-7556 http://www.health.auckland.ac.nz/pharmacology/staff/nholford/