上财系列LecturesonComputationalstatistics.ppt

Lectures on Computational Statistics Ying Chen School of Statistics and Management, SHUFE ychen@mail.shufe.edu.cn References Sheldon M. Ross, Simulation, 4th Edition.人民邮电出版社影印版，2007。 Angel R. Martinez, Wendy L. Martinez，Computational Statistics Handbook with MATLAB，Chapman Hall, CRC. 茆诗松、王静龙、濮晓龙 ，高等数理统计，高等教育出版社，1998。 王兆军，数理统计讲义，南开大学数学科学学院统计系，天津 高惠璇，统计计算，北京大学出版社，1995。 In general the constants a, c and m should be chosen to satisfy three criteria: For any initial seed, the resultant sequence has the “appearance” of being a sequence of independent uniform (0,1) random variables. For any initial seed, the number of variables that can be generated before repetition begins is large. The values can be computed efficiently on a digital computer. Example1: a=314159269, c=453806245, m=2^31. Example2: a=7^5, c=0, m=2^31-1. Chapter 4 Generating Discrete Random Variables Example 4d 4.2 Generating a Poisson Random Variable Another numerical example: MATLAB code Chapter 5 Generating Continuous Random Variables 5.1 The Inverse Transform Algorithm Simulating an Exponential Random 5.2 The Rejection Method Proposition. The random variable X generated by the rejection method has density function f. A numerical illustration 5.3 The polar method for generating normal random variables Random variable with MATLAB 3.4 Generating a Poisson Process 3.4 Generating a Poisson Process 5.5 Generating a Nonhomogeneous Poisson Process Chapter 7 Statistical Analysis of Simulated Data 7.1 The Sample Mean and Sample Variance 7.1 The Sample Mean and Sample Variance 7.1 The Sample Mean and Sample Variance 7.1 The Sample Mean and Sample Variance 7.1 The Sample Mean and Sample Variance 7.1 The Sample Mean and Sample Variance 7.2 Interval Estimates of a Population Mean 7.2 Interval Estimates of a Population Mean 7.2 Interval Estimates of a Population Mean 7.3 The Bootstrapping Technique for Estimating Mean Square Errors 7.3 The Bootstrapping Technique for Estimating Mean Square Errors 7.3 The Boots