期刊名称：Journal of Statistical Theory and Applications (JSTA)
电子版ISSN：1538-7887
出版年度：2015
卷号：14
期号：4
页码：383-398
DOI：10.2991/jsta.2015.14.4.4
语种：English
出版社：Atlantis Press
摘要：In this paper we consider an extension of the half-normal distribution based on the distribution of the maximum of a random sample. It is shown that this distribution belongs to the family of beta generalized half-normal distributions. Properties of its density are investigated, maximum likelihood estimation is discussed and the Fisher information matrix is derived. A real data illustration is presented, and comparisons with alternative extensions of the half-normal distribution reveal good performance of the proposed model.
关键词：Distribution of the maximum of a sample; Half-normal distribution; Maximum likelihood.
