Bayesian variable selection in high dimensional problems without assumptions on prior model probabilities
Methodology
2016-07-12 v1
Abstract
We consider the problem of variable selection in linear models when , the number of potential regressors, may exceed (and perhaps substantially) the sample size (which is possibly small).
Cite
@article{arxiv.1607.02993,
title = {Bayesian variable selection in high dimensional problems without assumptions on prior model probabilities},
author = {James O. Berger and Gonzalo Garcia-Donato and Miguel A. Martinez-Beneito and Victor Peña},
journal= {arXiv preprint arXiv:1607.02993},
year = {2016}
}