Back to Search Start Over

Flexible Multivariate Mixture Models: A Comprehensive Approach for Modeling Mixtures of Non‐Identical Distributions.

Authors :
Pal, Samyajoy
Heumann, Christian
Source :
International Statistical Review. Aug2024, p1. 36p. 21 Illustrations.
Publication Year :
2024

Abstract

Summary The mixture models are widely used to analyze data with cluster structures and the mixture of Gaussians is most common in practical applications. The use of mixtures involving other multivariate distributions, like the multivariate skew normal and multivariate generalised hyperbolic, is also found in the literature. However, in all such cases, only the mixtures of identical distributions are used to form a mixture model. We present an innovative and versatile approach for constructing mixture models involving identical and non‐identical distributions combined in all conceivable permutations (e.g. a mixture of multivariate skew normal and multivariate generalised hyperbolic). We also establish any conventional mixture model as a distinctive particular case of our proposed framework. The practical efficacy of our model is shown through its application to both simulated and real‐world data sets. Our comprehensive and flexible model excels at recognising inherent patterns and accurately estimating parameters. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
03067734
Database :
Academic Search Index
Journal :
International Statistical Review
Publication Type :
Academic Journal
Accession number :
178935029
Full Text :
https://doi.org/10.1111/insr.12593