A 250-year argument: Belief, behavior, and the bootstrap
HTML articles powered by AMS MathViewer
- by Bradley Efron PDF
- Bull. Amer. Math. Soc. 50 (2013), 129-146 Request permission
Abstract:
The year 2013 marks the 250th anniversary of Bayes rule, one of the two fundamental inferential principles of mathematical statistics. The rule has been influential over the entire period—and controversial over most of it. Its reliance on prior beliefs has been challenged by frequentism, which focuses instead on the behavior of specific estimates and tests under repeated use. Twentieth-century statistics was overwhelmingly behavioristic, especially in applications, but the twenty-first century has seen a resurgence of Bayesianism. Some simple examples are used to show what’s at stake in the argument. The bootstrap, a computer-intensive inference machine, helps connect Bayesian and frequentist practice, leading finally to an empirical Bayes example of collaboration between the two philosophies.References
- D. R. Bellhouse, The Reverend Thomas Bayes, FRS: a biography to celebrate the tercentenary of his birth, Statist. Sci. 19 (2004), no. 1, 3–43. With comments by Andrew Dale, A. W. F. Edwards, D. V. Lindley and Stephen M. Stigler and a rejoinder by the author. MR 2082145, DOI 10.1214/088342304000000189
- James Berger, The case for objective Bayesian analysis, Bayesian Anal. 1 (2006), no. 3, 385–402. MR 2221271, DOI 10.1214/06-BA115
- Julian Champkin, Beer and statistics, Significance 3 (2006), no. 3, 126–129. MR 2247161, DOI 10.1111/j.1740-9713.2006.00190.x
- Bradley Efron, Microarrays, empirical Bayes and the two-groups model, Statist. Sci. 23 (2008), no. 1, 1–22. MR 2431866, DOI 10.1214/07-STS236
- —, Bayesian inference and the parametric bootstrap, Submitted, Annals of Applied Statistics, 2012; connections between bootstrap and Bayes computation, the weighting curve of Figure 9, and Fisher’s correlation formula and the student score example.
- —, Tweedie’s formula and selection bias, J. Amer. Statist. Assoc. 106 (2011), no. 496, 1602–1614; discussion of the formula behind Figure 11.
- Robert E. Kass and Larry Wasserman, The selection of prior distributions by formal rules, J. Amer. Statist. Assoc. 91 (1996), no. 435, 1343–1370; thorough discussion of Jeffreys priors in their original and modern forms.
- E. L. Lehmann and Joseph P. Romano, Testing statistical hypotheses, 3rd ed., Springer Texts in Statistics, Springer, New York, 2005. MR 2135927
- Kantilal Varichand Mardia, John T. Kent, and John M. Bibby, Multivariate analysis, Probability and Mathematical Statistics: A Series of Monographs and Textbooks, Academic Press [Harcourt Brace Jovanovich, Publishers], London-New York-Toronto, Ont., 1979. MR 560319
Additional Information
- Bradley Efron
- Affiliation: Department of Statistics, 390 Serra Mall, Stanford, California 94305-4065
- Email: brad@stat.stanford.edu
- Received by editor(s): February 8, 2012
- Received by editor(s) in revised form: February 10, 2012
- Published electronically: April 25, 2012
- Additional Notes: The author’s work in supported in part by NIH grant 8R37 EB002784.
- © Copyright 2012
American Mathematical Society
The copyright for this article reverts to public domain 28 years after publication. - Journal: Bull. Amer. Math. Soc. 50 (2013), 129-146
- MSC (2010): Primary 97K70
- DOI: https://doi.org/10.1090/S0273-0979-2012-01374-5
- MathSciNet review: 2994997