A new compounding family of distributions: The generalized gamma power series distributions

详细信息    查看全文

• 作者：Rodrigo B. Silva^a ; ^{rodrigo@de.ufpb.br" class="auth_mail" title="E-mail the corresponding author} ; Marcelo Bourguignon^b ; ^{m.p.bourguignon@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Gauss M. Cordeiro^c ; ^{gausscordeiro@gmail.com" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Generalized gamma distribution ; Generating function ; Maximum likelihood estimator ; Moment ; Power series distribution
• 刊名：Journal of Computational and Applied Mathematics
• 出版年：2016
• 出版时间：September 2016
• 年：2016
• 卷：303
• 期：Complete
• 页码：119-139
• 全文大小：904 K

文摘

We propose a new four-parameter family of distributions by compounding the generalized gamma and power series distributions. The compounding procedure is based on the work by Marshall and Olkin (1997) and defines 76 sub-models. Further, it includes as special models the Weibull power series and exponential power series distributions. Some mathematical properties of the new family are studied including moments and generating function. Three special models are investigated in detail. Maximum likelihood estimation of the unknown parameters for complete sample is discussed. Two applications of the new models to real data are performed for illustrative purposes.