Skip to Content
Bayesian Statistics: An Introduction, 4th Edition
book

Bayesian Statistics: An Introduction, 4th Edition

by Peter M. Lee
September 2012
Intermediate to advanced
486 pages
10h 41m
English
Wiley
Content preview from Bayesian Statistics: An Introduction, 4th Edition

9.2 The EM algorithm

9.2.1 The idea of the EM algorithm

A useful numerical technique which finds the posterior mode, that is, the value at which  or equivalently  is a maximum, but does not provide full information on the posterior distribution is the EM algorithm. We can exemplify this by an example on genetic linkage due to Rao (1973, Section 5g) quoted by Dempster et al. (1977), by Gelfand and Smith (1990) and by Tanner (1996, Section 4.1). We have observations  with cell probabilities

Unnumbered Display Equation

and we want to estimate η. The likelihood is then

Unnumbered Display Equation

What we do is to augment the data  by adding further data  to produce augmented data  . It should be noted that to a considerable extent the distinction between ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Bayesian Data Analysis, Third Edition, 3rd Edition

Bayesian Data Analysis, Third Edition, 3rd Edition

Andrew Gelman, John B. Carlin, Hal S. Stern, David B. Dunson, Aki Vehtari, Donald B. Rubin
Introduction to Probability

Introduction to Probability

Joseph K. Blitzstein, Jessica Hwang

Publisher Resources

ISBN: 9781118359778Purchase book