s-news
[Top] [All Lists]

AIC for GLMM

To: s-news@lists.biostat.wustl.edu
Subject: AIC for GLMM
From: Nicola Koper <nkoper@yahoo.com>
Date: Mon, 2 Mar 2009 13:49:13 -0800 (PST)
Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s1024; t=1236030553; bh=vKzSFo+pZG0XW27TAWjhZQYs+TMyu3lApF3711ksMsw=; h=Message-ID:X-YMail-OSG:Received:X-Mailer:Date:From:Reply-To:Subject:To:MIME-Version:Content-Type; b=ZDfrFZjTMCQj68UtbhDSgs+HDPs7s+v6p4j7f1LjQ3lIAyQCligJydGys5bhJgbenmpPJCw6kVUWiJbuswRg/WBwVSXLuq+3SVBSm1ObLzW3We/iSl3e7zEt5hqNa6es5G0oXpD7iU5nu1hHBtHHzj8a4dlv2BsMaHx29XhteeA=
Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=Message-ID:X-YMail-OSG:Received:X-Mailer:Date:From:Reply-To:Subject:To:MIME-Version:Content-Type; b=BGJzvJ4VGgl1H7yFkYcVJlevP0U8NUCaTfdR44/9txsQK35akwgpGNaerTK5Iv4tx0e1kTmxknGYELSOMaa+Y+znwbE9XLw5+1mlKDjWucQprBgH6W4Yd2xMYJ+lGLe57GkH7/rpIfankcdsezpE3wVaaoUyQ+3ajx8WU+e6208=;
Reply-to: nkoper@yahoo.com
Hi everyone,
Still using Splus 6.2, with correlatedData add-on.
 
2 questions related to AIC and GLMM.
 
(1) Do any of the model estimation methods used by Splus in GLME produce a log-likelihood or approximation that's close enough to the log-likelihood that we can calculate an AIC value from it?
 
(2) If so, how do I get the log-likelihood or AIC value to be displayed?
 
Thank you,
Nicola Koper

<Prev in Thread] Current Thread [Next in Thread>
  • AIC for GLMM, Nicola Koper <=