Bayes Not Bust! Why Simplicity Is No Problem for Bayesians

British Journal for the Philosophy of Science 58 (4):709 - 754 (2007)
  Copy   BIBTEX

Abstract

The advent of formal definitions of the simplicity of a theory has important implications for model selection. But what is the best way to define simplicity? Forster and Sober ([1994]) advocate the use of Akaike's Information Criterion (AIC), a non-Bayesian formalisation of the notion of simplicity. This forms an important part of their wider attack on Bayesianism in the philosophy of science. We defend a Bayesian alternative: the simplicity of a theory is to be characterised in terms of Wallace's Minimum Message Length (MML). We show that AIC is inadequate for many statistical problems where MML performs well. Whereas MML is always defined, AIC can be undefined. Whereas MML is not known ever to be statistically inconsistent, AIC can be. Even when defined and consistent, AIC performs worse than MML on small sample sizes. MML is statistically invariant under 1-to-1 re-parametrisation, thus avoiding a common criticism of Bayesian approaches. We also show that MML provides answers to many of Forster's objections to Bayesianism. Hence an important part of the attack on Bayesianism fails

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 90,616

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Simplicity.Elliott Sober - 1975 - Oxford: Clarendon Press.
What is the problem of simplicity?Elliott Sober - 2001 - In Arnold Zellner, Hugo A. Keuzenkamp & Michael McAleer (eds.), Simplicity, Inference and Modelling: Keeping It Sophisticatedly Simple. New York: Cambridge University Press. pp. 13-32.
Statistical model selection criteria and bayesianism.I. A. Kieseppä - 2001 - Proceedings of the Philosophy of Science Association 2001 (3):S141 - S152.
AIC and large Samples.I. A. Kieseppä - 2003 - Philosophy of Science 70 (5):1265-1276.

Analytics

Added to PP
2009-01-28

Downloads
118 (#140,574)

6 months
16 (#109,309)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Steve Gardner
Monash University

References found in this work

A Mathematical Theory of Communication.Claude Elwood Shannon - 1948 - Bell System Technical Journal 27 (April 1924):379–423.
Predictive accuracy as an achievable goal of science.Malcolm R. Forster - 2002 - Proceedings of the Philosophy of Science Association 2002 (3):S124-S134.
Predictive Accuracy as an Achievable Goal of Science.Malcolm R. Forster - 2002 - Philosophy of Science 69 (S3):S124-S134.
Model selection in science: The problem of language variance.M. R. Forster - 1999 - British Journal for the Philosophy of Science 50 (1):83-102.

View all 6 references / Add more references