Khan, Shahjahan (2004) The role of the shape parameter in the estimation of the mean vector in multivariate Student-t population. International Journal of Statistical Sciences, 3 (Special volume in honour of Emeritus Professor M S Haq). pp. 69-89. ISSN 1683-5603
|HTML Citation||EndNote||Dublin Core||Reference Manager|
Full text not available from this archive.
The role of the shape parameter in determining the properties of the shrinkage and positive-rule shrinkage estimators of the mean vector of multivariate populations is of main interest in this paper. The preliminary test approach to shrinkage estimation is used to define two Stein-type estimators based on the sample information and uncertain prior non-sample information. The impact of the change in the value of the shape parameter on the performances of the estimators with respect to the criteria of unbiasedness and quadratic risk is investigated. Graphical analysis of the effect of the shape and dimension of the population on the above properties is also provided.
|Item Type:||Article (Commonwealth Reporting Category C)|
|Uncontrolled Keywords:||shrinkage and positive-rule; shrinkage estimators; shape parameter; quadratic bias and risk; multivariate normal and Student-t; inverted gamma; non-central chi-square; F- distributions; incomplete beta ratio|
|Fields of Research (FOR2008):||01 Mathematical Sciences > 0104 Statistics > 010405 Statistical Theory|
|Subjects:||230000 Mathematical Sciences > 230200 Statistics > 230203 Statistical Theory|
|Socio-Economic Objective (SEO2008):||E Expanding Knowledge > 97 Expanding Knowledge > 970101 Expanding Knowledge in the Mathematical Sciences|
|Deposited On:||11 Oct 2007 10:37|
|Last Modified:||12 Dec 2011 17:07|
Archive Staff Only: edit this record