Doubly reweighted estimators for the parameters of the multivariate t-distribution

Dogru F. Z., BULUT Y. M., ARSLAN O.

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, vol.47, no.19, pp.4751-4771, 2018 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 47 Issue: 19
  • Publication Date: 2018
  • Doi Number: 10.1080/03610926.2018.1445861
  • Journal Name: COMMUNICATIONS IN STATISTICS-THEORY AND METHODS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.4751-4771
  • Keywords: EM algorithm, ML, MLq, multivariate-t, REGRESSION-MODELS, ROBUST ESTIMATION, EM ALGORITHM, LIKELIHOOD, OUTLIERS
  • Eskisehir Osmangazi University Affiliated: Yes

Abstract

The t-distribution (univariate and multivariate) has many useful applications in robust statistical analysis. The parameter estimation of the t-distribution is carried out using maximum likelihood (ML) estimation method, and the ML estimates are obtained via the Expectation-Maximization (EM) algorithm. In this article, we will use the maximum Lq-likelihood (MLq) estimation method introduced by Ferrari and Yang (2010) to estimate all the parameters of the multivariate t-distribution. We modify the EM algorithm to obtain the MLq estimates. We provide a simulation study and a real data example to illustrate the performance of the MLq estimators over the ML estimators.