首页 | 本学科首页   官方微博 | 高级检索  
     检索      


A generalized Pólya urn model and related multivariate distributions
Authors:Kiyoshi Inoue  Sigeo Aki
Institution:(1) The Institute of Statistical Mathematics, 4-6-7 Minami-Azabu, Minato-ku, 106-8569 Tokyo, Japan;(2) Department of Informatics and Mathematical Science, Graduate School of Engineering Science, Osaka University, 1-3 Machikaneyama-cho, Toyonaka, 560-8531 Osaka, Japan;(3) Present address: Faculty of Economics, Seikei University, Kichijoji-Kitamachi, Musasino, 180-8633 Tokyo, Japan;(4) Present address: Department of Mathematics, Faculty of Engineering, Kansai University, Suita, 564-8680 Osaka, Japan
Abstract:In this paper, we study of Pólya urn model containing balls of (m+1) different labels under a general replacement scheme, which is characterized by an (m+1) × (m+1) addition matrix of integers without constraints on the values of these (m+1)2 integers other than non-negativity. LetX 1,X 2,...,X n be trials obtained by the Pólya urn scheme (with possible outcomes: “O”, “1”,...“m”). We consider the multivariate distributions of the numbers of occurrences of runs of different types arising from the various enumeration schemes and give a recursive formula of the probability generating function. Some closed form expressions are derived as special cases, which have potential applications to various areas. Our methods for the derivation of the multivariate run-related distribution are very simple and suitable for numerical and symbolic calculations by means of computer algebra systems. The results presented here develop a general workable framework for the study of Pólya urn models. Our attempts are very useful for understanding non-classic urn models. Finally, numerical examples are also given in order to illustrate the feasibility of our results. This research was partially supported by the ISM Cooperative Research Program (2003-ISM·CRP-2007).
Keywords:Pólya urn  replacement scheme  addition matrix  run  enumeration schemes  recursive scheme  probability generating function  double generating function  random structures
本文献已被 SpringerLink 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号