A new family of multivariate heavy-tailed distributions with variable marginal amounts of tailweights: Application to robust clustering - Archive ouverte HAL Access content directly
Journal Articles Statistics and Computing Year : 2014

A new family of multivariate heavy-tailed distributions with variable marginal amounts of tailweights: Application to robust clustering

(1) , (1)
1

Abstract

We propose a family of multivariate heavy-tailed distributions that allow variable marginal amounts of tailweight. The originality comes from introducing multidimensional instead of univariate scale variables for the mixture of scaled Gaussian family of distributions. In contrast to most existing approaches, the derived distributions can account for a variety of shapes and have a simple tractable form with a closed-form probability density function whatever the dimension. We examine a number of properties of these distributions and illustrate them in the particular case of Pearson type VII and ttails. For these latter cases, we provide maximum likelihood estimation of the parameters and illustrate their modelling flexibility on simulated and real data clustering example.
Fichier principal
Vignette du fichier
Rev2-ForHAL.pdf (1.97 Mo) Télécharger le fichier
Vignette du fichier
Rev2-sup_materials-ForbesWraithStatCo.pdf (384.04 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Other
Loading...

Dates and versions

hal-00823451 , version 1 (21-05-2013)
hal-00823451 , version 2 (24-07-2013)

Identifiers

Cite

Florence Forbes, Darren Wraith. A new family of multivariate heavy-tailed distributions with variable marginal amounts of tailweights: Application to robust clustering. Statistics and Computing, 2014, 24 (6), pp.971-984. ⟨10.1007/s11222-013-9414-4⟩. ⟨hal-00823451v2⟩
513 View
1618 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More