Journal article
Bayesian Estimation of Prediction Error and Variable Selection in Linear Regression
International statistical review, Vol.78(2), pp.257-270
Received May 2009, accepted February 2010
08/2010
DOI: 10.1111/j.1751-5823.2010.00115.x
Abstract
An important statistical application is the problem of determining an appropriate set of input variables for modelling a response variable. In such an application, candidate models are characterized by which input variables are included in the mean structure. A reasonable approach to gauging the propriety of a candidate model is to define a discrepancy function through the prediction error associated with this model. An optimal set of input variables is then determined by searching for the candidate model that minimizes the prediction error. In this paper, we focus on a Bayesian approach to estimating a discrepancy function based on prediction error in linear regression. It is shown how this approach provides an informative method for quantifying model selection uncertainty.
Details
- Title: Subtitle
- Bayesian Estimation of Prediction Error and Variable Selection in Linear Regression
- Creators
- Andrew A Neath - Department of Mathematics and Statistics, Southern Illinois University Edwardsville, Edwardsville, IL 62025, USAE-mail: aneath@siue.eduJoseph E Cavanaugh - Department of Biostatistics, The University of Iowa, 200 Hawkins Drive, C22 GH, Iowa City, IA 52242, USAE-mail: joe-cavanaugh@uiowa.edu
- Resource Type
- Journal article
- Publication Details
- International statistical review, Vol.78(2), pp.257-270
- Edition
- Received May 2009, accepted February 2010
- DOI
- 10.1111/j.1751-5823.2010.00115.x
- ISSN
- 0306-7734
- eISSN
- 1751-5823
- Publisher
- Blackwell Publishing Ltd
- Number of pages
- 14
- Language
- English
- Date published
- 08/2010
- Academic Unit
- Statistics and Actuarial Science; Biostatistics; Injury Prevention Research Center
- Record Identifier
- 9984214837602771
Metrics
38 Record Views