Bayesian bootstrap multivariate regression

Abstract

A Bayesian bootstrap multivariate regression (BBMR) procedure is presented that allows robust Bayesian analysis of multivariate regression models. BBMR does not require a parametric specification for the likelihood function and instead uses a bootstrapped likelihood based on the sampling distribution of location and scale estimators. A mixing algorithm for implementing the procedure automatically incorporates the scale invariant ignorance prior on the covariance matrix. BBMR can be implemented as a generic algorithm in standard statistical software independently of the actual choice of prior distribution. Monte Carlo evidence is provided showing accuracy and robustness of the approach in representing posterior distributions. © 2002 Elsevier Science B.V. All rights reserved.