Advances and Challenges in Inferences for Elliptically Contoured t Distributions
When a multivariate elliptical such as t response is taken from each of n individuals, the inference for the parameters of the t distribution including the location (or regression effects), scale and degrees of freedom (or shape) depends on the assumption whether n multi-dimensional responses are independent or uncorrelated but dependent. In the former case, that is, when responses are independent, the exact sampling theory based inference is extremely complicated, whereas in the later case the derivation of the exact sampling distributions for the standard statistics is manageable but the estimators based on certain standard statistics such as sample covariance matrix may be inconsistent for the respective parameters. In this paper we provide a detailed discussion on the advances and challenges in inferences using uncorrelated but dependent t samples. We then propose a clustered regression model where the multivariate t responses in the cluster are uncorrelated but such clustered responses are taken from a large number of independent individuals. The inference including the consistent estimation of the parameters of this proposed model is also presented.
KeywordsClustered regression model with uncorrelated t errors Consistent estimation Elliptically contoured distribution Multivariate t and normal as special cases Normality based testing yielding degrees of freedom based power property Regression effects Scale matrix Shape or degrees of freedom parameter
The author thanks the audience for their comments and suggestions.
- Amemiya, T.: Advanced Econometrics. Harvard University Press, Cambridge, MA (1985)Google Scholar
- Kubokawa, T., Srivastava, M.S.: Robust improvements in estimation of mean and covariance matrices in elliptically contoured distribution. Technical Report No. 9714. Department of Statistics, University of Toronto (1977)Google Scholar
- Pearson, K.: Tables of the Incomplete β-Function. University Press, London (1934)Google Scholar
- Student: Probable error of a correlation coefficient. Biometrika 6, 302–310 (1908)Google Scholar
- Sutradhar, B.C.: Multivariate t distribution. In: update volume 2 of Encyclopedia of Statistical Sciences. Wiley, New York, pp. 440–448 (1998)Google Scholar
- Sutradhar, B.C.: On the consistency of the estimators of the parameters of elliptically contoured distributions. In the special issue of Journal of Statistical Sciences published in honour of Professor M. S. Haq, U. W. O., ed. B.K. Sinha, Indian Statistical Institute, 3, 91–103 (2004)Google Scholar
- Sutradhar, B.C.: Dynamic Mixed Models for Familial Longitudinal Data. Springer Series in Statistics, 512 pp. Springer, New York (2011)Google Scholar
- Yuen, K.K., Murthy, V.K.: Percentage points of the t-distribution of the t statistic when the parent is Student’s t. Technometrics 16, 495–497 (1974)Google Scholar