dc.contributor.author |
Berger, JO |
|
dc.contributor.author |
Scott, James G |
|
dc.date.accessioned |
2011-06-21T17:30:35Z |
|
dc.date.issued |
2010-10-01 |
|
dc.identifier.issn |
0090-5364 |
|
dc.identifier.uri |
https://hdl.handle.net/10161/4408 |
|
dc.description.abstract |
This paper studies the multiplicity-correction effect of standard Bayesian variable-selection
priors in linear regression. Our first goal is to clarify when, and how, multiplicity
correction happens automatically in Bayesian analysis, and to distinguish this correction
from the Bayesian Ockham's-razor effect. Our second goal is to contrast empirical-Bayes
and fully Bayesian approaches to variable selection through examples, theoretical
results and simulations. Considerable differences between the two approaches are found.
In particular, we prove a theorem that characterizes a surprising aymptotic discrepancy
between fully Bayes and empirical Bayes. This discrepancy arises from a different
source than the failure to account for hyperparameter uncertainty in the empirical-Bayes
estimate. Indeed, even at the extreme, when the empirical-Bayes estimate converges
asymptotically to the true variable-inclusion probability, the potential for a serious
difference remains. © Institute of Mathematical Statistics, 2010.
|
|
dc.language.iso |
en_US |
|
dc.relation.ispartof |
Annals of Statistics |
|
dc.relation.isversionof |
10.1214/10-AOS792 |
|
dc.title |
Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problem |
|
dc.title.alternative |
|
|
dc.type |
Journal article |
|
dc.description.version |
Version of Record |
|
duke.date.pubdate |
2010-10-0 |
|
duke.description.issue |
5 |
|
duke.description.volume |
38 |
|
dc.relation.journal |
Annals of Statistics |
|
pubs.begin-page |
2587 |
|
pubs.end-page |
2619 |
|
pubs.issue |
5 |
|
pubs.organisational-group |
Duke |
|
pubs.organisational-group |
Statistical Science |
|
pubs.organisational-group |
Trinity College of Arts & Sciences |
|
pubs.publication-status |
Published |
|
pubs.volume |
38 |
|