Statistical inference for geometric processes with gamma distributions
Publication in refereed journal


香港中文大学研究人员 ( 现职)

梁燕萍教授 (那打素护理学院)

全文

数位物件识别号 (DOI) http://dx.doi.org/10.1016/j.csda.2003.12.004

引用次数
Web of Sciencehttp://aims.cuhk.edu.hk/converis/portal/Publication/10WOS source URL

其它资讯

摘要A stochastic process {X-i} is a geometric process if there exists a positive real number a such that {a(i-1) X-i} generates a renewal process. Under the assumption that X-1 follows a Gamma distribution, the statistical inference problem for the geometric process is studied. The parameters a, mu and sigma(2), where mu and sigma(2), are respectively, the mean and variance of X-1, are estimated by parametric methods including maximum likelihood method along with some nonparametric methods previously proposed by Y. Lam such as the modified moment method. Limiting distributions for the maximum likelihood estimators are derived and this enables us to construct confidence intervals and perform hypothesis testing on parameters. Then some suggestions on the choice of methods are made based on simulation experiments and real data analysis. (C) 2003 Published by Elsevier B.V.

着者Chan JSK, Lam Y, Leung DYP
期刊名称Computational Statistics and Data Analysis
出版年份2004
月份http://aims.cuhk.edu.hk/converis/portal/Publication/10
日期1
卷号47
期次3
出版社ELSEVIER SCIENCE BV
页次565 - 581
国际标準期刊号0167-9473
电子国际标準期刊号1872-7352
语言英式英语

关键词geometric process; maximum likelihood estimate; moment estimate; renewal process
Web of Science 学科类别Computer Science; Computer Science, Interdisciplinary Applications; COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS; Mathematics; Statistics & Probability; STATISTICS & PROBABILITY