Biometrika Advance Access published online on April 25, 2008
Biometrika, doi:10.1093/biomet/asn001
Articles |
Objective Bayesian analysis for the Student-t regression model
Department of Statistics, University of Warwick, Coventry CV4 7AL, U.K. T.C.O.Fonseca{at}warwick.ac.uk
Department of Statistics, University of Missouri, Columbia, Missouri 65211-6100, U.S.A. ferreiram{at}missouri.edu
Department of Statistics, Federal University of Rio de Janeiro, CEP: 21945-970, Brazil migon{at}im.ufrj.br
Received for publication 1 May 2006. Revision received 1 November 2007.
We develop a Bayesian analysis based on two different Jeffreys priors for the Student-t regression model with unknown degrees of freedom. It is typically difficult to estimate the number of degrees of freedom: improper prior distributions may lead to improper posterior distributions, whereas proper prior distributions may dominate the analysis. We show that Bayesian analysis with either of the two considered Jeffreys priors provides a proper posterior distribution. Finally, we show that Bayesian estimators based on Jeffreys analysis compare favourably to other Bayesian estimators based on priors previously proposed in the literature.
Key Words: Heavy tail behaviour • Jeffreys prior • Robustness to outliers
References
-
Abramowitz M., Stegun I. A. Handbook of Mathematical Functions (1986) New York: Dover.
Berger J., Pericchi L. The intrinsic Bayes factor for model selection and prediction. J. Am. Statist. Assoc. (1996) 91:109–22.[CrossRef][ISI]
Chib S., Nardari F., Shephard N. Markov chain Monte Carlo methods for stochastic volatility models. J. Economet. (2002) 108:281–316.[CrossRef]
Cribari-Neto F., Ferrari S. L. P., Cordeiro G. M. Improved heteroscedasticity-consistent covariance matrix estimators. Biometrika (2000) 87:907–18.
Fernández C., Steel M. F. J. On Bayesian modeling of fat tails and skewness. J. Am. Statist. Assoc. (1998) 93:359–71.[CrossRef][ISI]
Fernández C., Steel M. F. J. Multivariate Student-t regression models: Pitfalls and inference. Biometrika (1999) 86:153–67.
Geweke J. Bayesian treatment of the independent Student-t linear model. J. Appl. Economet. (1993) 8:519–40.
Greene W. H. Econometric Analysis (1997) Upper Saddle River, NJ: Prentice-Hall.
Jacquier E., Polson N. G., Rossi P. E. Bayesian analysis of stochastic volatility models with fat-tails and correlated errors. J. Economet. (2004) 122:185–212.[CrossRef]
Lange K. L., Little R. J. A., Taylor J. M. G. Robust statistical modeling using the t distribution. J. Am. Statist. Assoc. (1989) 84:881–96.[CrossRef][ISI]
Lavine M., Wolpert R. Discussion of a paper by A. O'Hagan. J. R. Statist. Soc. (1995) B 57:132.
Liu C. H. Missing data imputation using the multivariat t distribution. J. Mult. Anal. (1995) 53:139–58.[CrossRef]
Maronna R. A. Robust m-estimators of multivariate location and scatter. Ann. Statist. (1976) 4:51–67.[CrossRef]
O'Hagan A. Fractional Bayes factors for model comparison (with Discussion). J. R. Statist. Soc. (1995) B 57:99–138.
Vrontos I. D., Dellaportas P., Politis D. N. Full Bayesian inference for GARCH and EGARCH models. J. Bus. Econ. Statist. (2000) 18:187–98.[CrossRef]
West M. Outlier models and prior distributions in Bayesian linear regression. J. R. Statist. Soc. (1984) B 46:431–9.
CiteULike 
Connotea 
Del.icio.us What's this?
| ||||||||||||||||||||||||||||||||||||||||||||||||