RE: 95% CI of paramter estimate

From: Vladimir Piotrovskij Date: November 14, 2000 technical Source: cognigencorp.com
From: "Piotrovskij, Vladimir [JanBe]" <VPIOTROV@janbe.jnj.com> Subject: RE: 95% CI of paramter estimate Date: Tue, 14 Nov 2000 15:39:08 +0100 Jorn, Bootstrap seems to be the method of choice if you need CI for parameter estimates, however, it is almost impossible to do even for models of moderate complexity. BTW, CI based on SE provided by NONMEM are quite good for THETAs. In case of OMEGAs SE are less robust, but still reasonable. Note that most mixed-effects programs do not provide SE for random effects. Best regards, Vladimir ---------------------------------------------------------------------- Vladimir Piotrovsky, Ph.D. Janssen Research Foundation Clinical Pharmacokinetics (ext. 5463) B-2340 Beerse Belgium Email: vpiotrov@janbe.jnj.com

Thread

View all 14 messages
Nov 13, 2000 Joern Loetsch 95% CI of paramter estimate
Nov 13, 2000 Jogarao Gobburu Re: 95% CI of paramter estimate
Nov 13, 2000 Nick Holford Re: 95% CI of paramter estimate
Nov 14, 2000 Mats Karlsson Re: 95% CI of paramter estimate
Nov 14, 2000 Leonid Gibiansky RE: 95% CI of parameter estimate
Nov 14, 2000 Vladimir Piotrovskij RE: 95% CI of paramter estimate
Nov 14, 2000 Mats Karlsson Re: 95% CI of parameter estimate
Nov 14, 2000 Leonid Gibiansky RE: 95% CI of parameter estimate
Nov 15, 2000 Michael Smith RE: 95% CI of parameter estimate
Nov 15, 2000 James Wright RE: 95% CI of parameter estimate
Nov 17, 2000 Matt Hutmacher RE: 95% CI of parameter estimate
Nov 17, 2000 Nick Holford Re: 95% CI of parameter estimate
Nov 20, 2000 Matt Hutmacher RE: 95% CI of parameter estimate
Nov 21, 2000 Vladimir Piotrovskij RE: 95% CI of paramter estimate
← Previous
Next →