Two level stochastic search variable selection in GLMs with missing predictors


Mitra, Robin and Dunson, David D. (2009) Two level stochastic search variable selection in GLMs with missing predictors. Southampton, UK, Southampton Statistical Sciences Research Institute, 28pp. (S3RI Methodology Working Papers, (M09/04) ).

Download

[img] PDF - Pre print
Download (215Kb)

Description/Abstract

Stochastic search variable selection (SSVS) algorithms provide an appealing and widely used approach for searching for good subsets of predictors, while simultaneously estimating posterior model probabilities and model-averaged predictive distributions. This article proposes a two-level generalization of SSVS to account for missing predictors, while accommodating uncertainty in the relationships between these predictors. Bayesian approaches for allowing predictors that are missing at random require a model on the joint distribution of the predictors. We show that predictive performance can be improved by allowing uncertainty in the specification of this model. The methods are illustrated through simulation studies and analysis of an epidemiologic data set.

Item Type: Monograph (Working Paper)
Keywords: missing at random, model averaging, multiple imputation, stochastic search, subset selection, variable selection
Subjects: H Social Sciences > HA Statistics
Divisions: University Structure - Pre August 2011 > Southampton Statistical Sciences Research Institute
ePrint ID: 65460
Date Deposited: 17 Feb 2009
Last Modified: 27 Mar 2014 18:46
URI: http://eprints.soton.ac.uk/id/eprint/65460

Actions (login required)

View Item View Item

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics