Bayesian Inference of a Multivariate Regression Model

We explore Bayesian inference of a multivariate linear regression model with use of a flexible prior for the covariance structure. The commonly adopted Bayesian setup involves the conjugate prior, multivariate normal distribution for the regression coefficients and inverse Wishart specification for...

Full description

Saved in:
Bibliographic Details
Main Authors: Marick S. Sinay, John S. J. Hsu
Format: Article
Language:English
Published: Wiley 2014-01-01
Series:Journal of Probability and Statistics
Online Access:http://dx.doi.org/10.1155/2014/673657
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849686965790703616
author Marick S. Sinay
John S. J. Hsu
author_facet Marick S. Sinay
John S. J. Hsu
author_sort Marick S. Sinay
collection DOAJ
description We explore Bayesian inference of a multivariate linear regression model with use of a flexible prior for the covariance structure. The commonly adopted Bayesian setup involves the conjugate prior, multivariate normal distribution for the regression coefficients and inverse Wishart specification for the covariance matrix. Here we depart from this approach and propose a novel Bayesian estimator for the covariance. A multivariate normal prior for the unique elements of the matrix logarithm of the covariance matrix is considered. Such structure allows for a richer class of prior distributions for the covariance, with respect to strength of beliefs in prior location hyperparameters, as well as the added ability, to model potential correlation amongst the covariance structure. The posterior moments of all relevant parameters of interest are calculated based upon numerical results via a Markov chain Monte Carlo procedure. The Metropolis-Hastings-within-Gibbs algorithm is invoked to account for the construction of a proposal density that closely matches the shape of the target posterior distribution. As an application of the proposed technique, we investigate a multiple regression based upon the 1980 High School and Beyond Survey.
format Article
id doaj-art-01b23de824d2436bbfc46880213670fe
institution DOAJ
issn 1687-952X
1687-9538
language English
publishDate 2014-01-01
publisher Wiley
record_format Article
series Journal of Probability and Statistics
spelling doaj-art-01b23de824d2436bbfc46880213670fe2025-08-20T03:22:30ZengWileyJournal of Probability and Statistics1687-952X1687-95382014-01-01201410.1155/2014/673657673657Bayesian Inference of a Multivariate Regression ModelMarick S. Sinay0John S. J. Hsu1ZestFinance, 6636 Hollywood Boulevard, Los Angeles, CA 90028, USADepartment of Statistics and Applied Probability, University of California, Santa Barbara, CA 93106, USAWe explore Bayesian inference of a multivariate linear regression model with use of a flexible prior for the covariance structure. The commonly adopted Bayesian setup involves the conjugate prior, multivariate normal distribution for the regression coefficients and inverse Wishart specification for the covariance matrix. Here we depart from this approach and propose a novel Bayesian estimator for the covariance. A multivariate normal prior for the unique elements of the matrix logarithm of the covariance matrix is considered. Such structure allows for a richer class of prior distributions for the covariance, with respect to strength of beliefs in prior location hyperparameters, as well as the added ability, to model potential correlation amongst the covariance structure. The posterior moments of all relevant parameters of interest are calculated based upon numerical results via a Markov chain Monte Carlo procedure. The Metropolis-Hastings-within-Gibbs algorithm is invoked to account for the construction of a proposal density that closely matches the shape of the target posterior distribution. As an application of the proposed technique, we investigate a multiple regression based upon the 1980 High School and Beyond Survey.http://dx.doi.org/10.1155/2014/673657
spellingShingle Marick S. Sinay
John S. J. Hsu
Bayesian Inference of a Multivariate Regression Model
Journal of Probability and Statistics
title Bayesian Inference of a Multivariate Regression Model
title_full Bayesian Inference of a Multivariate Regression Model
title_fullStr Bayesian Inference of a Multivariate Regression Model
title_full_unstemmed Bayesian Inference of a Multivariate Regression Model
title_short Bayesian Inference of a Multivariate Regression Model
title_sort bayesian inference of a multivariate regression model
url http://dx.doi.org/10.1155/2014/673657
work_keys_str_mv AT marickssinay bayesianinferenceofamultivariateregressionmodel
AT johnsjhsu bayesianinferenceofamultivariateregressionmodel