The skew-normal distribution has gained widespread application across various domains due to its flexibility in modeling asymmetric data. However, accurately estimating its parameters-particularly the shape parameter-as well as those of its extended families such as the truncated or multivariate skew-normal distributions, remains a significant challenge. This paper presents a brief theoretical review of two primary parameter estimation methods: Maximum Likelihood Estimation (MLE) and Weighted Moment Estimation (WMM). For the MLE approach, we further investigate the effectiveness of reparameterization techniques in enhancing numerical stability. The advantages, limitations, and computational behavior of both methods are thoroughly examined. Results indicate that reparameterization substantially improves the stability of MLE, while WMM demonstrates superior performance in scenarios involving small sample sizes or high skewness. In contrast, MLE may underperform in complex or extreme data settings. These findings provide valuable guidance for researchers in selecting appropriate estimation strategies and lay the groundwork for the development of more robust estimation methods in future studies.
목차
Abstract 1. Introduction 2. Distribution 2.1. Multivariate skew-normal distribution 2.2. Closed skew-normal distribution 3. Parameter Estimation Methods 3.1. Maximum likelihood estimation 3.2. Weighted Moment Estimation 3.3. Graphical summary of Parameter Estimation methods 4. Discussion References
키워드
Skew-normal distributionMaximum likelihood estimationReparametrizationWeighted moment estimation
저자
Zhuolin Liu [ Department of Statistics, Chonnam National Universtiy, Gwangju 61186, Korea ]
Yunbu Cong [ Department of Statistics, Chonnam National Universtiy, Gwangju 61186, Korea ]
Jaesik Jeong [ Department of Statistics, Chonnam National Universtiy/Big data Research Lab, Chonnam National University, Gwangju 61186, Korea ]
Corresponding Author
조선대학교 기초과학연구원 [The Natural Science Research Institute of Chosun]
설립연도
2008
분야
자연과학>자연과학일반
소개
본 연구원은 기초과학을 진흥하기 위한 연구·교육 및 그 보급을 목적으로 한다. 이 목적을 달성하기 위하여 다음 각 호의 사업을 수행한다.
1. 기초과학 제 분야에 관한 조사와 연구
2. 기초과학에 관한 학술행사(학술대회, 학술세미나, 심포지엄, 초청강연회 등) 개최
3. 학문후속세대 및 일반인을 위한 기초과학 교육
4. 기관지『조선자연과학논문지』 발간
5. 『자연과학연구총서』, 『자연과학번역총서』 등 단행본 발간
6. 기타 본 연구원의 목적과 관련된 사업
간행물
간행물명
통합자연과학논문집(구 조선자연과학논문집) [Journal of Integrative Natural Science]