期刊文献+

The Gaussian approximation for generalized Friedman's urn model with heterogeneous and unbalanced updating

The Gaussian approximation for generalized Friedman's urn model with heterogeneous and unbalanced updating
原文传递
导出
摘要 The Friedman's urn model is a popular urn model which is widely used in many disciplines.In particular,it is extensively used in treatment allocation schemes in clinical trials.Its asymptotic properties have been studied by many researchers.In literature,it is usually assumed that the expected number of balls added at each stage is a constant in despite of what type of balls are selected,that is,the updating of the urn is assumed to be balanced.When it is not,the asymptotic property of the Friedman's urn model is stated in the book of Hu and Rosenberger(2006) as one of open problems in the area of adaptive designs.In this paper,we show that both the urn composition process and the allocation proportion process can be approximated by a multi-dimensional Gaussian process almost surely for a general multi-color Friedman type urn model with heterogeneous and unbalanced updating.The Gaussian process is a solution of a stochastic differential equation.As an application,we obtain the asymptotic properties including the asymptotic normality and the exact law of the iterated logarithm. The Friedman's urn model is a popular urn model which is widely used in many disciplines. In particular, it is extensively used in treatment allocation schemes in clinical trials. Its asymptotic properties have been studied by many researchers. In literature, it is usually assumed that the expected number of balls added at each stage is a constant in despite of what type of balls are selected, that is, the updating of the urn is assumed to be balanced. When it is not, the asymptotic property of the Friedman's urn model is stated in the book of Hu and Rosenberger (2006) as one of open problems in the area of adaptive designs. In this paper, we show that both the urn composition process and the allocation proportion process can be approximated by a multi-dimensional Gaussian process almost surely for a general multi-color Friedman type urn model with heterogeneous and unbalanced updating. The Gaussian process is a solution of a stochastic differential equation. As an application, we obtain the asymptotic properties including the asymptotic normality and the exact law of the iterated logarithm.
作者 ZHANG LiXin
出处 《Science China Mathematics》 SCIE 2012年第11期2379-2404,共26页 中国科学:数学(英文版)
基金 supported by National Natural Science Foundation of China (Grant No.11071214) Natural Science Foundation of Zhejiang Province (Grant No. R6100119) the Program for New Century Excellent Talents in University (Grant No. NCET-08-0481) Department of Education of Zhejiang Province(Grant No. 20070219)
关键词 Gaussian approximation the law of iterated logarithm asymptotic normality urn model urn模型 弗里德曼 不平衡 异质性 高斯近似 广义 渐近性质 随机微分方程
  • 相关文献

参考文献2

二级参考文献17

  • 1Li-xinZhang.Strong Approximations of Martingale Vectors and Their Applications in Markov-Chain Adaptive Designs[J].Acta Mathematicae Applicatae Sinica,2004,20(2):337-352. 被引量:3
  • 2Bai, Z.D., Hu, F. Asymptotic theorem for urn models with nonhomogeneous generating matrices. Stochastic Process. Appl., 80:87-101 (1999).
  • 3Bai, Z.D., Hu,F., Zhang L.X. The Gaussian approximation theorems for urn models and their applications.Ann. Appl. Probab., 12:1149-1173 (2002).
  • 4Eberlein, E. On strong invariance principles under dependence. Ann. Probab., 14:260-270 (1986).
  • 5Eisele, Ji, Woodroofe, M. Central limit theorems for doubly adaptive biased coin designs. Ann. Statist.,23:234-254 (1995).
  • 6Hall.P,Heyde,C.C. Martingale Limit Theory and its Applications. Academic Press, London, 1980.
  • 7Hoel, D.G., Sobel, M. Comparison of sequential procedures for selecting the best binomial population.Proc. Sixth. Berkeley Syrup. Math. Statist. and Probabilities, 4:53-69 (1972).
  • 8Hu, F., Zhang, L.X. Asymptotic properties of doubly adaptive biased coin designs for multi-treatment clinical trials. Ann. Statist., 32:268-301 (2004).
  • 9Monrad, D., Philipp, W. The problem of embedding vector-valued martingales in a Gaussian process.Teor. Vero.yatn. Primen., 35:384-387 (1990).
  • 10Monrad, D., Philipp, W. Nearby variabies with nearby conditional laws and a strong approximation theorem for Hilbert sDace valued martingales. Probab. Theory Relat. Fields, 88:381-404 (1991).

共引文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部