Multivariate Student -t Regression Models : Pitfalls and Inference

We consider likelihood-based inference from multivariate regression models with independent Student-t errors. Some very intruiging pitfalls of both Bayesian and classical methods on the basis of point observations are uncovered. Bayesian inference may be precluded as a consequence of the coarse nature of the data. Global maximization of the likelihood function is a vacuous exercise since the likelihood function is unbounded as we tend to the boundary of the parameter space. A Bayesian analysis on the basis of set observations is proposed and illustrated by several examples.

[1]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[2]  E. L. Lehmann,et al.  Theory of point estimation , 1950 .

[3]  A. Zellner.  An Efficient Method of Estimating Seemingly Unrelated Regressions and Tests for Aggregation Bias , 1962 .

[4]  J. W. Gorman,et al.  Fitting Equations to Data. , 1973 .

[5]  D. F. Andrews,et al.  A Robust Method for Multiple Linear Regression , 1974 .

[6]  O. Kempthorne,et al.  Maximum Likelihood Estimation in the Three‐Parameter Lognormal Distribution , 1976 .

[7]  R. Maronna.  Robust $M$-Estimators of Multivariate Location and Scatter , 1976 .

[8]  Ramanathan Gnanadesikan,et al.  Methods for statistical data analysis of multivariate observations , 1977, A Wiley publication in applied statistics.

[9]  Daniel A. Relles,et al.  Statisticians are Fairly Robust Estimators of Location , 1977 .

[10]  M. Pagano,et al.  The application of robust calibration to radioimmunoassay. , 1979, Biometrics.

[11]  M. West.  Outlier Models and Prior Distributions in Bayesian Linear Regression , 1984 .

[12]  F. R. Gantmakher.  The Theory of Matrices , 1984 .

[13]  Anthony N. Pettitt,et al.  Re‐Weighted Least Squares Estimation with Censored and Grouped Data: An Application of the EM Algorithm , 1985 .

[14]  Russell C. H. Cheng,et al.  Corrected Maximum Likelihood in Non‐Regular Problems , 1987 .

[15]  Richard J. Beckman,et al.  Fitting the student- t distribution to grouped data, with application to a particle scattering experiment , 1987 .

[16]  S. Kotz,et al.  Symmetric Multivariate and Related Distributions , 1989 .

[17]  Jeremy MG Taylor,et al.  Robust Statistical Modeling Using the t Distribution , 1989 .

[18]  P. Rousseeuw,et al.  Unmasking Multivariate Outliers and Leverage Points , 1990 .

[19]  Adrian F. M. Smith,et al.  Sampling-Based Approaches to Calculating Marginal Densities , 1990 .

[20]  G. Casella,et al.  Explaining the Gibbs Sampler , 1992 .

[21]  J. Geweke,et al.  Bayesian Treatment of the Independent Student- t Linear Model , 1993 .

[22]  K. Lange,et al.  Normal/Independent Distributions and Their Applications in Robust Regression , 1993 .

[23]  Jun S. Liu,et al.  Sequential Imputations and Bayesian Missing Data Problems , 1994 .

[24]  D. Rubin,et al.  The ECME algorithm: A simple extension of EM and ECM with faster monotone convergence , 1994 .

[25]  Chuanhai Liu,et al.  Missing data imputation using the multivariate t distribution , 1995 .

[26]  Chuanhai Liu.  Bayesian robust multivariate linear regression with incomplete data , 1996 .

[27]  Mark F. J. Steel,et al.  On the Dangers of Modelling through Continuous Distributions: A Bayesian Perspective , 1997 .