Identiﬁability of Finite Mixture Models with underlying Normal Distribution

Reference : Identiﬁability of Finite Mixture Models with underlying Normal Distribution


	Document type :	E-prints/Working papers : First made available on ORBilu
	Discipline(s) :	Physical, chemical, mathematical & earth Sciences : Mathematics
	To cite this reference:	http://hdl.handle.net/10993/45317

Title :	Identiﬁability of Finite Mixture Models with underlying Normal Distribution
Language :	English
Author, co-author :	Noel, Cédric [Université de Lorraine > IUT de Thionville-Yutz]
	Schiltz, Jang [University of Luxembourg > Faculty of Law, Economics and Finance (FDEF) > Department of Finance (DF) >]
Publication date :	2020
Number of pages :	13
Peer reviewed :	No
Keywords :	[en] Identifiability ; Finite Mixture Models ; Normal Distribution
Abstract :	[en] In this paper, we show under which conditions generalized ﬁnite mixture with underlying normal distribution are identiﬁable in the sense that a given dataset leads to a uniquely determined set of model parameter estimations up to a permuta-tion of the clusters.
Permalink :	http://hdl.handle.net/10993/45317

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	2020_2 Identifiability.pdf		Author postprint	335.5 kB	View/Open

All documents in ORBi^lu are protected by a user license.