Hostname: page-component-7b7567c8c-9cwtv Total loading time: 0 Render date: 2026-11-19T16:44:49.429Z Has data issue: false hasContentIssue false

On identifiability of mixtures of independent distributionlaws∗∗∗∗∗∗

Published online by Cambridge University Press:  01 July 2014

Mikhail Kovtun
Affiliation:
Duke University, Dept. of Biology, Benfey Lab Durham, 27708 NC, USA. mikhail.kovtun@duke.edu
Igor Akushevich
Affiliation:
Center for Population Health and Aging Durham, 27708 NC, USA; igor.akushevich@duke.edu; anatoly.yashin@duke.edu
Anatoliy Yashin
Affiliation:
Center for Population Health and Aging Durham, 27708 NC, USA; igor.akushevich@duke.edu; anatoly.yashin@duke.edu

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

We consider representations of a joint distribution law of a family of categorical randomvariables (i.e., a multivariate categorical variable) as a mixture ofindependent distribution laws (i.e. distribution laws according to whichrandom variables are mutually independent). For infinite families of random variables, wedescribe a class of mixtures with identifiable mixing measure. This class is interestingfrom a practical point of view as well, as its structure clarifies principles of selectinga “good” finite family of random variables to be used in applied research. For finitefamilies of random variables, the mixing measure is never identifiable; however, it alwayspossesses a number of identifiable invariants, which provide substantial informationregarding the distribution under consideration.

Information

Type
Research Article
Copyright
© EDP Sciences, SMAI 2014