FINITE MIXTURES OF MULTIVARIATE SKEW LAPLACE DISTRIBUTIONS


DOĞRU F. Z., BULUT Y. M., ARSLAN O.

REVSTAT-STATISTICAL JOURNAL, vol.19, no.1, pp.35-46, 2021 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 19 Issue: 1
  • Publication Date: 2021
  • Journal Name: REVSTAT-STATISTICAL JOURNAL
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, zbMATH
  • Page Numbers: pp.35-46
  • Keywords: EM algorithm, ML estimation, multivariate mixture model, MSL
  • Eskisehir Osmangazi University Affiliated: Yes

Abstract

This paper proposes finite mixtures of multivariate skew Laplace distributions in order to model both skewness and heavy-tailedness in heterogeneous data sets. Maximum likelihood estimators for the parameters of interest are obtained using the EM algorithm. The paper offers a small simulation study and a real data example to illustrate the performance of the proposed mixture model.