User: Guest  Login
Document type:
Zeitschriftenaufsatz 
Author(s):
Czado, C. and Raftery, A.E. 
Title:
Choosing the link function and accounting for link uncertainty in generalized linear models using Bayes factors 
Abstract:
One important component of model selection using generalized linear models (GLM) is the choice of a link function. We propose using approximate Bayes factors to assess the improvement in fit over a GLM with canonical link when a parametric link family is used. The approximate Bayes factors are calculated using the Laplace approximations given in [32], together with a reference set of prior distributions. This methodology can be used to differentiate between different parametric link families...    »
 
Keywords:
Bayes factors; link function; GLM, model selection; reference prior. 
Journal title:
Statistical Papers 
Year:
2006 
Journal volume:
47 
Journal issue:
Pages contribution:
419-442 
Reviewed:
ja 
Language:
en 
Status:
Verlagsversion / published 
Semester:
SS 06 
Format:
Text