蒙特卡罗统计方法

2009-10  

世界图书出版公司  

（法）罗伯特　著  

645  

无  

He sat，continuing to look down the nave，when suddenly the solution to the problem just seemed to present itself．It was so simple，SO obvious he just started to laugh——P．C．Doherty．Satan in St Mary'sMonte Carlo statistical methods，particularly those based on Markov chains，have now matured to be part of the standard set of techniques used by statisticians．This book is intended to bring these techniques into the classroom． being(we hope)a self-contained logical development of the subject，with all concepts being explained in detail．and all theorems．etc．having detailed proofs．There is also an abundance of examples and problems，relating the concepts with statistical practice and enhancing primarily the application of simulation techniques to statistical problems of various difficulties．This iS a textbook intended for a second-year graduate course．We do not assume that the reader has any familiarity with Monte Carlo techniques (such as random variable generation)or with any Markov chain theory. We do assume that the reader has had a first course in statistical theory at the level of Statistica!Inference bY Casella and Berger(1990)．Unfortunately，a few times throughout the book a somewhat more advanced notion iS needed．We have kept these incidents to a minimum and have posted warnings when they occur．While this iS a book on simulation．whose actual implementation must be processed through a computer，no requirement lS made on programming skills or computing abilities：algorithms are presented in a program-like format but in plain text rather than in a specific programming language．(Most of the examples in the book were actually implemented in C．with the S-Plus graphical interface.)

It is a tribute to our profession that a textbook that was current in 1999 is starting to feel old. The work for the first edition of Monte Carlo Statistical Methods (MCSM1) was finished in late 1998, and the advances made since then, as well as our level of understanding of Monte Carlo methods, have grown a great deal. Moreover, two other things have happened. Topics that just made it into MCSM1 with the briefest treatment (for example, perfect sampling) have now attained a level of importance that necessitates a much more thorough treatment. Secondly, some other methods have not withstood the test of time or, perhaps, have not yet been fully developed, and now receive a more appropriate treatment. When we worked on MCSM1 in the mid-to-late 90s, MCMC algorithms were already heavily used, and the flow of publications on this topic was atsuch a high level that the picture was not only rapidly changing, but also necessarily incomplete. Thus, the process that we followed in MCSM1 was that of someone who was thrown into the ocean and was trying to grab onto the biggest and most seemingly useful objects while trying to separate the flotsam from the jetsam. Nonetheless, we also felt that the fundamentals of many of these algorithms were clear enough to be covered at the textbook alevel, so we" swam on.

作者：(法国)罗伯特(Christian P.Robert) (法国)George Casella

Preface to the Second EditionPreface to the First Edition1　Introduction　1.1 Statistical Models　1.2 Likelihood Methods　1.3 Bayesian Methods　1.4 Deterministic Numerical Methods　　1.4.1 Optimization　　1.4.2 Integration　　1.4.3 Comparison 　1.5 Problems 　1.6 Notes 　　1.6.1 Prior Distributions 　　1.6.2 Bootstrap Methods2 Random Variable Generation　2.1 Introduction　　2.1.1 Uniform Simulation　　2.1.2 The Inverse Transform　　2.1.3 Alternatives　　2.1.4 Optimal Algorithms　2.2 General Transformation Methods　2.3 Accept Reject Methods　　2.3.1 The Fundamental Theorem of Simulation　　2.3.2 The Accept-Reject Algorithm.　2.4 Envelope Accept Reject Methods　　2.4.1 The Squeeze Principle 　　2.4.2 Log-Concave Densities　2.5 Problems 　2.6 Notes　　 2.6.1 The Kiss Generator　　 2.6.2 Quasi-Monte Carlo Methods　　 2.6.3 Mixture Representations3 Monte Carlo Integration　3.1 Introduction　3.2 Classical Monte Carlo Integration　3.3 Importance Sampling　　3.3.1 Principles　　3.3.2 Finite Variance Estimators　　3.3.3 Comparing Importance Sampling with Accept-Reject 　3.4 Laplace Approximations　3.5 Problems　3.6 Notes　　3.6.1 Large Deviations Techniques 　　3.6.2 The Saddlepoint Approximation4 Controling Monte Carlo Variance　4.1 Monitoring Variation with the CLT　　4.1.1 Univariate Monitoring　　4.1.2 Multivariate Monitoring　4.2 Rao-Blackwellization 　4.3 RieInann Approximations　4.4 Acceleration Methods　　4.4.1 Antithetic Variables　　 4.4.2 Control Variates　4.5 Problems　4.6 Notes　　 4.6.1 Monitoring Importance Sampling Convergence　　 4.6.2 Accept Reject with Loose Bounds　　 4.6.3 Partitioning5 Monte Carlo Optimization　 5.1 Introduction　 5.2 Stochastic Exploration　　 5.2.1 A Basic Solution　　 5.2.2 Gradient Methods　　 5.2.3. Simulated Annealing　　 5.2.4 Prior Feedback　5.3 Stochastic Approximation　　 5.3.1 Missing Data Models and Demarginalization　　 5.3.2 The EM Algorithm　　 5.3.3 Monte Carlo EM　　 5.3.4 EM Standard Errors ……6　Markov Chains7 The Metropolis-Hastings Algorithm8 The Slice Sampler9 The Two-Stage Gibbs Sampler10 The Multi-Stage Gibbs Sampler11 Variable Dimension Models and Reversible Jump Algorithms12 Diagnosing Convergence13 Perfect Sampling 14 Iterated and Sequential Importance Sampling A Probability DistributionsB NotationReferencesIndex

插图：

《蒙特卡罗统计方法(第2版)(英文版)》由世界图书出版公司出版。

无

蒙特卡罗统计方法 PDF格式下载

看到有的读者评价这本书为“蒙特卡洛数学”，想说说自己的观点。
Monte Carlo本来就是一种很复杂的算法，要讲解清楚本来就需要大量数学语言。
正如书名所写，这本书绝非纯粹讲解Monte Carlo，而是其在统计学中的应用，以及由此而发展出来的一些统计方法。
市面上Monte Carlo统计的教材非常少，要么偏重算法的角度，要么是从Bayesian ***pution的角度出发。而这本书内容自洽，讲解详细，绝对是学习Monte Carlo统计ods的绝佳教材。

今天拿到了新书，随手翻阅了若干内容，感觉对于我这样之前没有接触过蒙特卡罗的人来说，这本书正合适入门，内容由浅及深，相当经典！

全文都不英文，阅读起来有点慢，不过外国人学的比较直接！里面大部分都不是统计论的公式，要有高等数学和数理统计的基础！书不错

完全看不懂啊亲T T不过还是给个五分送当当的发货速度吧

书非常好，内容很全面、详尽。

这本书挺好！下次还来当当购书！

全英文的，介绍的很详细。

书看着还行。。。没仔细看呢。。。不过这次没给俺开发票。。。快递态度不怎么地。。。。望当当注意这些细节。。。。

这本蒙卡的书比较数学，侧重从原理上来讲解蒙卡到底是怎么一会儿事，有不少例子和算法。
但，比较难，如果是没接触过蒙卡，上来就看这个，估计会很吃力，如果是做过一段蒙卡，有一定的基础，针对自己的具体问题再回到书中来深入了解，倒是一本挺好的书。
总之我觉得这本书确切的名字叫，蒙特卡洛的数学原理更贴切些吧。

嗯，内容不错，虽然英文版读起来费劲点

书还不错，到货很快

书是好书，但有轻度磨损，不知道是哪个环节出了问题。希望下次注意。

侧重于数学基本理论的书。
装订质量一般。

非统计专业路过,所以乍看起来还是有点费力,但是内容确实翔实,springer出版的肯定不会差，可惜robert的blog现在看不了，希望对bayesian和mcmc有兴趣的同学能够拿起来看看，肯定会有所收获的

内容详细深入，是学习MC方法的好书

刚拿到，看了看目录，虽然是英文的读起来可能有困难，但是真的不错，内容很全面

不知道是不是包装的事儿，书都破了，内容嘛，有待研究，拿回来做研究用的！~~

买的时候还犹豫了一下，买完看了一点，真值！

该书用一种让人非常费解的方式描述问题，并且语言也大多是抽象的。感觉是如果一个问题你以前知道，那么你知道他在讲什么，如果你以前不知道，那么你看了他的书仍然不知道。不适合初学者。该书有一点好处是习题很多。

感觉不错，挺好的。英文，但是读起来还是行。

基本快要看完了，写的很好，容易读懂！

效果看上去还不错，比较满意

印刷质量不行，内容就不说了，可惜的是印刷的不够清晰，令我对影印版有些失望