What is Markov Chain Monte Carlo and Why it Matters
1st Edition
Published on 31. December 2023
Book
Hardback
200 pages
978-1-138-10641-3 (ISBN)
Description
This book presents a narrative account of Markov Chain Monte Carlo at a popular level. The author relies on history to provide a unifying narrative thread; on the centuries-old tension between "classical" and Bayesian approaches, as a plot theme that can highlight the importance of MCMC in changing the practice of statistics; and on applied examples and on metaphor in the hope of conveying the concepts without making technical demands of the reader.
More details
Language
English
Place of publication
London
United Kingdom
Publishing group
Taylor & Francis Ltd
Target group
Professional and scholarly
Illustrations
30 s/w Abbildungen
30 Illustrations, black and white
Dimensions
Height: 234 mm
Width: 156 mm
ISBN-13
978-1-138-10641-3 (9781138106413)
Copyright in bibliographic data is held by Nielsen Book Services Limited or its licensors: all rights reserved.
Schweitzer Classification
Person
George Cobb was chair in 1990-1991 of the focus group on statistics of the Mathematical Association of America and from 1990 to 1999 of the Joint Committee on Undergraduate Statistics of the Mathematical Association of America and the American Statistical Association. He served on the committee that founded the Journal of Statistical Education in 1993 and then was its associate editor for five years. He served on the Committee on Applied and Theoretical Statistics of the National Academy of Sciences. In 1993 he was elected a fellow of the American Statistical Association and in June 2003 was elected to serve a three-year term as vice president of that organization. He has published two books, Introduction to Design and Analysis of Experiments (Springer Verlag, 1998), and Statistics in Action: Practical Principles for a World of Uncertainty (Key Curriculum Press, 2003)
Content
An enduring controversy. The story of Bernoulli's Law of Averages. The story of Bayes's theorem. The triumphs of Laplace and Gauss. The triumphs of Fisher and Neyman. The provocations of Brinbaum, Savage, and de Finetti. The computational obstruction. A computational breakthrough. The bomb, the computer, and the origins of Monte Carlo methods. Metropolis and Hastings. The Gemans; Gelfand and Smith. The Gibbs sampler. Hierarchical models. Statistics: No definitive answers; only evolving questions. Subjective or objective? The role of priors. Equal ignorance and the paradox of flat priors. Jeffries and the attempt at "objective priors." Reanalysis and sensitivity analysis.