Re: Help: Non-positive semi-definite message

From: Nick Holford <n.holford@auckland.ac.nz> Subject: Re: Help: Non-positive semi-definite message Date: Wed, 22 Aug 2001 11:10:43 +1200 Ken, If you use PPC and rely only the data set at hand then I would not take on the bet. But if your PPC included an informative prior about the value of the covariance then I would be happy to bet you a six pack :-) Let me know when you have the results and I'll provide a six pack of your favourite if you can demonstrate that the PPC with an uninformative prior is better than one with a prior covariance of 0.3 and lets say a CV of 50% for the precision of this prior. Nick -- Nick Holford, Divn Pharmacology & Clinical Pharmacology University of Auckland, 85 Park Rd, Private Bag 92019, Auckland, New Zealand email:n.holford@auckland.ac.nz tel:+64(9)373-7599x6730 fax:373-7556 http://www.phm.auckland.ac.nz/Staff/NHolford/nholford.htm