NobleBlocks

Research index

Bayesian Methods

Dempster

Wiley StatsRef: Statistics Reference Online29 Sep 2014

NobleIDark:/48914/w1/20260515/028D25E7DOI10.1002/9781118445112.stat05825

Paywalled

The full text is at the publisher

You can read the abstract here, or open it at the publisher.

Read at the publisher

Abstract

Abstract Bayesian methods are used in the analysis of statistical data to provide posterior (postdata) probabilities for hypotheses. These are calculated, by Bayes' theorem, from prior (predata) probabilities and the likelihood function obtained from the observed data. Probabilities may be “objective” or “subjective”, representing degrees of belief. The history of this approach is surveyed. It fell out of fashion during the first half of the twentieth century, under the influences of the different frequentist approaches of Fisher and Neyman, but interest was maintained by the work of Jeffreys and de Finetti and revived in the mid‐1950s through the work of Savage and others. The article discusses problems arising in contemporary work, such as the involvement of many parameters, aspects of modeling, and availability of computing methods, and summarizes arguments for and against Bayesian methods.

Discussion

Citations

Topics

More

Suggest a correction or report