Dimension reduction for model-based clustering via mixtures of multivariate $$t$$t-distributions

Authors:
Katherine Morris;Paul D. Mcnicholas;Luca Scrucca
Affiliations:
Department of Mathematics and Statistics, University of Guelph, Ontario, Canada;Department of Mathematics and Statistics, University of Guelph, Ontario, Canada;Dipartimento di Economia, Finanza e Statistica, Università degli Studi di Perugia, Perugia, Italy
Venue:
Advances in Data Analysis and Classification
Year:
2013

Citing 13
Cited 0

Robust mixture modelling using the t distribution

Statistics and Computing
Extension of the mixture of factor analyzers model to incorporate the multivariate t-distribution

Computational Statistics & Data Analysis
Parsimonious Gaussian mixture models

Statistics and Computing
Model-based clustering with non-elliptically contoured distributions

Statistics and Computing
Constrained monotone EM algorithms for mixtures of multivariate t distributions

Statistics and Computing
Robust mixture modeling using multivariate skew t distributions

Statistics and Computing
Model-based classification via mixtures of multivariate t-distributions

Computational Statistics & Data Analysis
Dimension reduction for model-based clustering

Statistics and Computing
Model-based clustering of microarray expression data via latent Gaussian mixture models

Bioinformatics
Mixtures of common t-factor analyzers for clustering high-dimensional microarray data

Bioinformatics
Extending mixtures of multivariate t-factor analyzers

Statistics and Computing
Simultaneous model-based clustering and visualization in the Fisher discriminative subspace

Statistics and Computing
Model-based clustering, classification, and discriminant analysis via mixtures of multivariate t-distributions

Statistics and Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce a dimension reduction method for model-based clustering obtained from a finite mixture of $$t$$t-distributions. This approach is based on existing work on reducing dimensionality in the case of finite Gaussian mixtures. The method relies on identifying a reduced subspace of the data by considering the extent to which group means and group covariances vary. This subspace contains linear combinations of the original data, which are ordered by importance via the associated eigenvalues. Observations can be projected onto the subspace and the resulting set of variables captures most of the clustering structure available in the data. The approach is illustrated using simulated and real data, where it outperforms its Gaussian analogue.