Bayesian Estimation of Unknown Regression Error Heteroscedasticity

Hiroaki Chigira
Tsunemasa Shiba

March 2009 (Revised: April 2009)

Abstract

We propose a Bayesian procedure to estimate heteroscedastic variances of the regression error term ω, when the form of heteroscedasticity is unknown. The prior information on ω is elicited from the wellknown Eicker–White Heteroscedasticity Consistent Variance–Covariance Matrix Estimator. Markov Chain Monte Carlo algorithm is used to simulate posterior pdf’s of the unknown elements of ω. In addition to the numerical examples, we present an empirical investigation of the stock prices of Japanese pharmaceutical and biomedical companies to demonstrate usefulness of the proposed method.

Full text

PDF Download (PDF: 672KB)