@globomaxnm.com
Subject: RE: [NMusers] Different EBE estimation between original and
enriched dataset with MDV=1
Pascal:
There is one more consideration. If your model depends on the use of
covariate data, then during the numerical integration from time t1 to
t2, where t1 and t2 are times of two
regards,
Pascal
From: Leonid Gibiansky lgibian...@quantpharm.com
To: pascal.gir...@merckgroup.com
Cc: nmusers@globomaxnm.com nmusers@globomaxnm.com
Date: 26/11/2012 21:40
Subject: Re: [NMusers] Different EBE estimation between original and
enriched dataset with MDV=1
: Sunday, November 25, 2012 9:11 PM
To: Leonid Gibiansky; pascal.gir...@merckgroup.com
Cc: nmusers@globomaxnm.com
Subject: RE: [NMusers] Different EBE estimation between original and enriched
dataset with MDV=1
Pascal:
There is one more consideration. If your model depends on the use of covariate
Struemper herbert.x.struem...@gsk.com
To: nmusers@globomaxnm.com nmusers@globomaxnm.com
Date: 26/11/2012 16:13
Subject:RE: [NMusers] Different EBE estimation between original
and enriched dataset with MDV=1
Sent by:owner-nmus...@globomaxnm.com
Pascal,
I had the same issue
, It's a kind og magic! :-)
From: Herbert Struemper herbert.x.struem...@gsk.com
To: nmusers@globomaxnm.com nmusers@globomaxnm.com
Date: 26/11/2012 16:13
Subject: RE: [NMusers] Different EBE estimation between original and
enriched dataset with MDV=1
Sent by: owner-nmus...@globomaxnm.com
] Different EBE estimation between original and enriched
dataset with MDV=1
Hi Pascal,
In addition to Leonid's answer, if you have time-varying covariates and aren't
explicitly computing the current value in the $DES block and are interpolating
them (with something other than LOCF), that could
[mailto:owner-nmus...@globomaxnm.com] On
Behalf Of Leonid Gibiansky
Sent: Friday, November 23, 2012 12:15 PM
To: pascal.gir...@merckgroup.com
Cc: nmusers@globomaxnm.com
Subject: Re: [NMusers] Different EBE estimation between original and enriched
dataset with MDV=1
Hi Pascal,
I think the problem
Dear Pascal,
What you observed is related to “speed” of estimation. With a larger dataset
(many dummies) you slow down the estimation. Roughly similar to using the
SLOW command in $EST. With an estimation that has difficulties to converge
you see a difference in EBEs and other parameters. We