gBF: A Fully Bayes Factor with a Generalized g-prior

For the normal linear model variable selection problem, we propose selection criteria based on a fully Bayes formulation with a generalization of Zellner’s g-prior which allows for p > n. A special case of the prior formulation is seen to yield tractable closed forms for marginal densities and Bayes factors which reveal new model characteristics of potential interest. AMS 2000 subject classifications: Primary 62F07, 62F15; secondary 62C10.

[1]  Clifford M. Hurvich,et al.  Regression and time series model selection in small samples , 1989 .

[2]  George Casella,et al.  Condition Numbers and Minimax Ridge Regression Estimators , 1985 .

[3]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[4]  J. Geluk,et al.  Regular variation, extensions and Tauberian theorems , 1987 .

[5]  H. Zou The Adaptive Lasso and Its Oracle Properties , 2006 .

[6]  William E. Strawderman,et al.  A new class of generalized Bayes minimax ridge regression estimators , 2004 .

[7]  G. Schwarz Estimating the Dimension of a Model , 1978 .

[8]  Edward I. George,et al.  Empirical Bayes vs. Fully Bayes Variable Selection , 2008 .

[9]  Dean Phillips Foster,et al.  Calibration and Empirical Bayes Variable Selection , 1997 .

[10]  W. Strawderman Proper Bayes Minimax Estimators of the Multivariate Normal Mean , 1971 .

[11]  M. Clyde,et al.  Mixtures of g Priors for Bayesian Variable Selection , 2008 .

[12]  H. Akaike A new look at the statistical model identification , 1974 .

[13]  George Casella,et al.  Minimax Ridge Regression Estimation , 1980 .

[14]  Dean P. Foster,et al.  The risk inflation criterion for multiple regression , 1994 .

[15]  M. Steel,et al.  Benchmark Priors for Bayesian Model Averaging , 2001 .

[16]  Wenjiang J. Fu,et al.  Asymptotics for lasso-type estimators , 2000 .

[17]  A. Zellner,et al.  Posterior odds ratios for selected regression hypotheses , 1980 .

[18]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .