Bayesian analysis of mixture models with Yeo-Johnson transformation

Abstract-Mixture models are widely employed in the analysis of heterogeneous data. However, existing approaches are based on the assumption that the observations in each component are normally distributed. The main objective of this article is to propose mixture models with Yeo-Johnson transformatio...

Full description

Saved in:

Bibliographic Details
Published in:	Communications in statistics. Theory and methods Vol. 53; no. 18; pp. 6600 - 6613
Main Authors:	Cai, Jingheng, Xu, Xiaoli
Format:	Journal Article
Language:	English
Published:	Philadelphia Taylor & Francis 16-09-2024 Taylor & Francis Ltd
Subjects:	Bayesian analysis Data analysis Markov chain Monte Carlo methods mixture distributions Mixtures Yeo-Johnson transformation
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Abstract-Mixture models are widely employed in the analysis of heterogeneous data. However, existing approaches are based on the assumption that the observations in each component are normally distributed. The main objective of this article is to propose mixture models with Yeo-Johnson transformation to handle general heterogeneous data. Bayesian methods are developed for estimation and model comparison. The empirical performance of the proposed methodology is assessed through simulation studies. A real analysis of a data set derived from the National Longitudinal Survey of Youth 1997 is presented for illustration.
ISSN:	0361-0926 1532-415X
DOI:	10.1080/03610926.2023.2248326