RE: Parameterization!!!

From: Leonid Gibiansky Date: May 09, 2001 technical Source: cognigencorp.com
From: "Gibiansky, Leonid" <gibianskyl@globomax.com> Subject: RE: Parameterization!!! Date: Wed, 9 May 2001 16:47:50 -0400 I would guess that the difference is due to the correlation of ETAs (you may check it by plotting individual estimates of ETA1 vs ETA2 or CL vs V2). Try block structure of the OMEGA matrix. Example: CL=THETA(1)*EXP(ETA(1)) V2=THETA(2)*EXP(ETA(2)) $OMEGA BLOCK(2) 1 0.1 1 If you use correlated structure with TRANS1 and TRANS4 (correlating pairs of alternative parameters) you may get closer results. Leonid

Thread

View all 16 messages
May 08, 2001 Sreenivasa Rao Vanapalli Parameterization!!!
May 09, 2001 Atul Bhattaram Venkatesh Re: Parameterization!!!
May 09, 2001 William Bachman RE: Parameterization!!!
May 09, 2001 Leonid Gibiansky RE: Parameterization!!!
May 09, 2001 Nick Holford Re: Parameterization!!!
May 09, 2001 Sreenivasa Rao Vanapalli Parameterization!!!
May 10, 2001 Nick Holford Re: Parameterization!!!
May 10, 2001 Jean Xavier Mazoit Re: Parameterization!!!
May 10, 2001 Stephen Duffull RE: Parameterization!!!
May 10, 2001 Nick Holford Re: Parameterization!!!
May 10, 2001 Leonid Gibiansky RE: Parameterization!!!
May 10, 2001 Kenneth G. Kowalski RE: Parameterization!!!
May 10, 2001 Mats Karlsson Re: Parameterization!!!
May 10, 2001 Jean Xavier Mazoit Re: Parameterization!!!
May 11, 2001 Leonid Gibiansky RE: Parameterization!!!
May 13, 2001 Mats Karlsson Re: Parameterization!!!
← Previous
Next →