s-news
[Top] [All Lists]

/x?.FPMB.CBz4qtG.QNumrRg.a

To: s-news@lists.biostat.wustl.edu
Subject: /x?.FPMB.CBz4qtG.QNumrRg.a
From: "Dora C PEARCE" <dpearce@students.ballarat.edu.au>
Date: Sun, 29 Jul 2007 10:42:42 +1000
Reply-to: dpearce@students.ballarat.edu.au
Dear S list,
I have run a spatial linear regression model using a CAR covariance matrix and, 
in addition to obtaining  a significant association between the dependent and 
independent variables, get a negative log-likelihood  (= -6.176). However, when 
I add a factor and an interaction term as additional explanatory variables, the 
log-likelihood is positive (= 1.794).

Is it OK to have a POSITIVE log-likelihood, or does this mean there is a 
misspecification problem?

Thank you in advance for your advice,
Kind regards,
Dora
Dora Pearce
PhD student
School of Science & Engineering
University of Ballarat
PO Box 663, Ballarat, Victoria, 3353
Email: dpearce@students.ballarat.edu.au
Ph: (03) 5327 9264

<Prev in Thread] Current Thread [Next in Thread>
  • /x?.FPMB.CBz4qtG.QNumrRg.a, Dora C PEARCE <=