OPTIMAL B-ROBUST ESTIMATORS FOR THE PARAMETERS OF THE GENERALIZED HALF-NORMAL DISTRIBUTION


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

REVSTAT-STATISTICAL JOURNAL, vol.15, no.3, pp.455-471, 2017 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 15 Issue: 3
  • Publication Date: 2017
  • Journal Name: REVSTAT-STATISTICAL JOURNAL
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.455-471
  • Keywords: generalized half-normal, optimal B-robust, maximum likelihood
  • Eskisehir Osmangazi University Affiliated: Yes

Abstract

The purpose of this study is to propose robust estimators by using optimal B-robust (OBR) estimation method (Hampel et al. [5]) for the parameters of the generalized half-normal (GHN) distribution. After given the robust estimators, we provide a small simulation study to compare its performance with the estimators obtained from maximum likelihood (ML) estimation method. We also give a real data example to illustrate the performance of the proposed estimators.