Summary
Motivated by attractive features of inferences based on heavy-tailed distributions, we develop Bayesian inference for the location parameter of a family of location-scaled distributions, which are shifted and scaled Studentt and normal distributions. The family of prior distributions utilized to the unknown location and squared-scale consists of independent Studentt and inverted gamma distributions. When observations are sampled from at distribution, the likelihood estimators are intractable. Thus, we use MML (modified maximum likelihood) estimators instead to develop Bayesian inference. Bayesian estimators are defined by modes of posterior densities and called HPD (highest posterior density) estimators. The proposed estimators, especially the estimators arising from at distribution, are clearly superior. They adjust automatically to the sample dispersion, ignore inconsistent information, and are rather insensitive to outliers. The posterior density of the location parameter may be bimodal. Posterior bimodality indicates some conflicts between the two sources of information: the sample and the prior knowledge. We also report the results of simulation studies that point toward overall superiority of the proposed estimators.
Similar content being viewed by others
References
Angers, J. F. and Berger, J. O. (1991). Robust hierarchical Bayesian estimation of exchangeable means.Canadian J. Statist. 19, 39–56.
Barnett, V. D. (1966). Order statistics estimators of the location of the Cauchy distribution.J. Amer. Statist. Assoc. 61, 1205–1218.
Berger, J. O. (1980). A robust generalized Bayes estimator and confidence region for a multivariate normal mean.Ann. Statist. 8, 716–761.
Bhattacharyya, G. K. (1985). The asymptotic of maximum likelihood and related estimators based on Type II censored data.J. Amer. Statist. Assoc. 80, 398–404.
Bian, G. (1989). Bayesian statistical analysis with independent bivariate priors for the normal location and scale parameters. Ph.D. Thesis, University of Minnesota.
Bian, G. (1995). Robust Bayesian estimators in a one-way ANOVA model.Test 4, 115–135.
Bian, G. and Dickey, J. M. (1996). Properties of multivariate Cauchy and poly-Cauchy distributions with Bayesiang-prior applications. Bayesian Analysis in Statistics and Econometrics: Essays in Honor of Arnold Zellner (D. A. Berry, K. M. Chaloner and J. K. Geweke, eds.) New York: Wiley, 299–310.
Bian, G. and Tiku, M. L. (1996). Bayesina inference based on robust priors and MML estimators: Part I, symmetric location-scale distributions. Statistics (to appear).
Carlin, B. P. and Polson, N. G. (1991). Inference for nonconjugate Bayesian models using the Gibbs sampler.Canadian J. Statist. 19, 399–406.
Dawid, A. P. (1973). Posterior expectations for large observations.Biometrika 60, 664–667.
DeFinetti, B. (1961). The Bayesian approach to the rejection of outliers. Proceedings of the fourth Berkeley Symposium on Probability and Statistics (Vol. 1). Berkeley, University of California Press, 199–210.
Dickey, J. M. (1968). Three multimensional-integral identities with Bayesian applications.Ann. Statist. 39, 1615–1627.
Dickey, J. M. (1974). Bayesian alternatives to the F-test and least-squares estimate in the normal linear model. Studies in Bayesian Econometrics and Statistics (S. E. Fienberg and A. Zellner, eds.), Amsterdam: North-Holland, 515–554.
Dreze, J. H. (1977). Bayesian regression analysis using poly-t densities. J. Econometrics 6, 329–354.
Dreze, J. H. and Richard, J-F. (1983). Bayesian analysis of simultaneous equation system. Handbook of Econometrics 1 (Z. Glriliches and M. D. Intriligator, eds.). Amsterdam: North-Holland, 577–598.
Gelfand, A. E., Hills, S. E., Racine-Poon, A. and Smith, A. F. M. (1990). Illustration of Bayesian inference in normal data model using Gibbs sampling.J. Amer. Statist. Assoc. 85, 972–985.
Hill, B. M. (1974). On coherence inadmissibility and inference about many parameters in the theory of least squares. Studies in Bayesian Econometrics and Statistics (S. E. Fienberg and A. Zellner, eds.). Amsterdam: North-Holland, 555–584.
Lindley, D. V. and Smith, A. F. M. (1972). Bayes estimators for the linear model.J. Roy. Statist. Soc. B 34, 1–41.
Lucas, T. W. (1993). When is conflict normal?J. Amer. Statist. Assoc. 88, 1433–1437.
O’Hagan, A. (1979). On outlier rejection phenomena in Bayes inference.J. Roy. Statist. Soc. B 41, 358–367.
O’hagan, A. (1988). Modelling with heavy tails.Bayesian Statistics 3 (J. M. Bernardo, M. H. DeGroot, D. V. Lindley and A. F. M. Smith, eds.). Oxford: University Press, 345–359.
O’Hagan, A. (1990). Outliers and credence for location parameter inference.J. Amer. Statist. Assoc. 85, 172–176.
Pericchi, L. R. and Smith, A. F. M. (1992). Exact and approximate posterior moments for normal location parameter.J. Roy. Statist. Soc. B. 54, 793–804.
Raiffa, H. and Schlaifer, R. (1961).Applied Statistical Decision Theory Boston: Harvard University.
Ramsey, J. O. and Novick, M. R. (1980). PLU robust Bayesian decision theory: point estimation.J. Amer. Statist. Assoc. 75, 401–407.
Richard, J.-F. and Tompa, H. (1980). On the evaluation of poly-t density function.J. Econometrics 12, 335–351.
Stone, M. (1964). Comments on a posterior distribution of Geisser and Cornfield.J. Roy. Statis. Soc. B 26, 274–276.
Tiao, G.C. and Zellner, A. (1964). On the Bayesian estimation of multivariate regression.J. Roy. Statist. Soc. B 26, 277–285.
Tierney, L. and Kadane, J. B. (1986). Accurate approximation for posterior moments and marginal densities.J. Amer. Statist. Assoc. 81, 82–86.
Tiku, M. L. (1982). Testing linear contrasts of means in experimental design without assuming normality and homogeneity of variances.Biometrical J. 24, 613–627 (invited paper).
Tiku, M. L. and Kumra, S. (1981). Expected values and variances and covariances of order statistics for a family of symmetric distributions (Student’st). Selected Tables in Mathematical Statistics 8, 141–270. The American Math. Society: Providence, Rhode Island.
Tiku, M. L., Tan, W. Y. and Balakrishnan, N. (1986).Robust Inference. New York: Marcel Dekker.
Tiku, M. L. and Suresh, R. D. (1992). A new method of estimation for location and scale parameters.J. Statist. Plann. and Inf. 30, 281–292.
Vaughan, D.C. (1992). On the Tiku-Suresh method of estimation.Commun. Statist-Theory Meth. 21, 451–469.
West, M. (1983). Generalized linear models: scale parameters, outlier accommodation and prior distributions.Bayesian Statiscs 2 (J. M. Bernardo, M. H. DeGroot, D. V. Lindley and A. F. M. Smith, eds.), Amsterdam: North-Holland, 531–558. (with discussion).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Bian, G. Bayesian inference in location-scale distributions with independent bivariate priors. Test 6, 137–157 (1997). https://doi.org/10.1007/BF02564431
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02564431