Identifiability of Finite Mixtures of Elliptical Distributions
We present general results on the identifiability of finite mixtures of elliptical distributions under conditions on the characteristic generators or density generators. Examples include the multivariate "t"-distribution, symmetric stable laws, exponential power and Kotz distributions. In each case, the shape parameter is allowed to vary in the mixture, in addition to the location vector and the scatter matrix. Furthermore, we discuss the identifiability of finite mixtures of elliptical densities with generators that correspond to scale mixtures of normal distributions. Copyright 2006 Board of the Foundation of the Scandinavian Journal of Statistics..
Year of publication: |
2006
|
---|---|
Authors: | HOLZMANN, HAJO ; MUNK, AXEL ; GNEITING, TILMANN |
Published in: |
Scandinavian Journal of Statistics. - Danish Society for Theoretical Statistics, ISSN 0303-6898. - Vol. 33.2006, 4, p. 753-763
|
Publisher: |
Danish Society for Theoretical Statistics Finnish Statistical Society Norwegian Statistical Association Swedish Statistical Association |
Saved in:
Saved in favorites
Similar items by person
-
Tests in a Case-Control Design Including Relatives
Biedermann, Stefanie, (2006)
-
Nonparametric confidence bands in deconvolution density estimation
Bissantz, Nicolai, (2007)
-
The authors replied as follows:
Holzmann, Hajo, (2008)
- More ...