Statistical Science

The Future of Indirect Evidence

Bradley Efron

Full-text: Open access


Familiar statistical tests and estimates are obtained by the direct observation of cases of interest: a clinical trial of a new drug, for instance, will compare the drug’s effects on a relevant set of patients and controls. Sometimes, though, indirect evidence may be temptingly available, perhaps the results of previous trials on closely related drugs. Very roughly speaking, the difference between direct and indirect statistical evidence marks the boundary between frequentist and Bayesian thinking. Twentieth-century statistical practice focused heavily on direct evidence, on the grounds of superior objectivity. Now, however, new scientific devices such as microarrays routinely produce enormous data sets involving thousands of related situations, where indirect evidence seems too important to ignore. Empirical Bayes methodology offers an attractive direct/indirect compromise. There is already some evidence of a shift toward a less rigid standard of statistical objectivity that allows better use of indirect evidence. This article is basically the text of a recent talk featuring some examples from current practice, with a little bit of futuristic speculation.

Article information

Statist. Sci., Volume 25, Number 2 (2010), 145-157.

First available in Project Euclid: 19 November 2010

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Statistical learning experience of others Bayesian and frequentist James–Stein Benjamini–Hochberg False Discovery Rates effect size


Efron, Bradley. The Future of Indirect Evidence. Statist. Sci. 25 (2010), no. 2, 145--157. doi:10.1214/09-STS308.

Export citation


  • Benjamini, Y. and Hochberg, Y. (1995). Controlling the false discovery rate: A practical and powerful approach to multiple testing. J. Roy. Statist. Soc. Ser. B 57 289–300.
  • Benjamini, Y. and Yekutieli, D. (2005). False discovery rate-adjusted multiple confidence intervals for selected parameters. J. Amer. Statist. Assoc. 100 71–93.
  • Brown, L. D. (1971). Admissible estimators, recurrent diffusions, and insoluble boundary value problems. Ann. Math. Statist. 42 855–903.
  • Efron, B. (1998). R. A. Fisher in the 21st century (invited paper presented at the 1996 R. A. Fisher Lecture). Statist. Sci. 13 95–122.
  • Efron, B. (2003). Robbins, empirical Bayes and microarrays. Ann. Statist. 31 366–378.
  • Efron, B. (2004). Large-scale simultaneous hypothesis testing: The choice of a null hypothesis. J. Amer. Statist. Assoc. 99 96–104.
  • Efron, B. (2008a). Microarrays, empirical Bayes and the two-groups model. Statist. Sci. 23 1–22.
  • Efron, B. (2008b). Simultaneous inference: When should hypothesis testing problems be combined? Ann. Appl. Statist. 2 197–223.
  • Efron, B. (2009). Empirical Bayes estimates for large-scale prediction problems. J. Amer. Statist. Assoc. To appear.
  • Efron, B. and Morris, C. (1977). Stein’s paradox in statistics. Scientific American 236 119–127.
  • Golub, T. R., Slonim, D. K. and Tamayo, P. et al. (1999). Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring. Science 286 531–537.
  • Hastie, T., Tibshirani, R. and J. Friedman (2008). The Elements of Statistical Learning, 2nd ed. Springer, New York.
  • Lemley, K. V., Lafayette, R. A., Derby, G., Blouch, K. L., Anderson, L., Efron, B. and Myers, B. D. (2008). Prediction of early progression in recently diagnosed IgA nephropathy. Nephrol. Dialysis Transplant. 23 213–222.
  • Miller, R. G., Jr. (1981). Simultaneous Statistical Inference, 2nd ed. Spring, New York.
  • Schwartzman, A., Dougherty, R. and Taylor, J. (2005). Cross-subject comparison of principal diffusion direction maps. Magnetic Resonance in Medicine 53 1423–1431.
  • Senn, S. (2008). A note concerning a selection “paradox” of Dawid’s. Amer. Statist. 62 206–210.
  • Singh, D., Febbo, P. G., Ross, K., Jackson, D. G., Manola, J., Ladd, C., Tamayo, P., Renshaw, A. A., D’Amico, A. V., Richie, J. P., Lander, E. S., Loda, M., Kantoff, P. W., Golub, T. R. and Sellers, W. R. (2002). Gene expression correlates of clinical prostate cancer behavior. Cancer Cell 1 203–209.
  • Stein, C. M. (1956). Inadmissibility of the usual estimator for the mean of a multivariate normal distribution. In Proc. Third Berkeley Symp. Math. Statist. Probab. Vol. I 197–206. Univ. California Press, Berkeley.