Twenty-one years ago, when this paper first appeared, I was a graduate student asking myself the very question posed in the title of Brad Efron’s paper. Bayesians were saviors or crackpots depending on who you asked. Philosophical arguments in favor of and against Bayesian inference were common. Applications using Bayesian methods were not so common. This changed with the advent of Markov chain Monte Carlo methods. Data analyses rooted in Bayesian methods abound. Indeed, Bayesian techniques are used in numerous fields including biology, medicine, physics, ecology, public policy, image recovery and many more. And yet, for all the reasons given in Efron’s article, frequentist thinking, not subjectivism, is still dominant in the field of statistics. But in related fields, like machine learning, Bayesian thinking does seems to be much more prevalent. So, on the occasion of Efron’s 70th birthday, it seems entirely appropriate to reprint and revisit this paper.
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
Wasserman, L. (2008). Why isn't Everyone a Bayesian?. In: Morris, C.N., Tibshirani, R. (eds) The Science of Bradley Efron. Springer Series in Statistics. Springer, New York, NY. https://doi.org/10.1007/978-0-387-75692-9_13
Download citation
DOI: https://doi.org/10.1007/978-0-387-75692-9_13
Publisher Name: Springer, New York, NY
Print ISBN: 978-0-387-75691-2
Online ISBN: 978-0-387-75692-9
eBook Packages: Mathematics and Statistics (R0)