## Should the default significance level be changed from 0.05 to 0.005?

My comments in this discussion of “Redefine statistical significance”:

The call for smaller significance levels cannot be based only on mathematical arguments that p values tend to be much lower than posterior probabilities, as Andrew Gelman and Christian Robert pointed out in their comment (“Revised evidence for statistical standards”).

In the rejoinder, Valen Johnson made it clear that the call is also based on empirical findings of non-reproducible research results. How many of those findings are significant at the 0.005 level? Should meta-analysis have a less stringent standard?

…

“Irreplicable results can’t possibly add empirical clout to the mathematical argument unless it is already known or assumed to be caused by a given cut-off, and further, that lowering it would diminish those problems.”

The preprint cites empirical results to support its use of the 1:10 prior odds. If that is in fact a reliable estimate of the prior odds for the reference class of previous studies, then, in the absence of other relevant information, it would be reasonable to use as input for Bayes’s theorem.

John Byrd asks, “Is 1:10 replicable?” Is it important to ask whether a 1:1 prior odds can be rejected at the 0.005 significance level?

END

## Inference to the best explanation of the evidence

The *p* value and Bayesian methods have well known drawbacks when it comes to measuring the strength of the evidence supporting one hypothesis over another. To overcome those drawbacks, this paper proposes an alternative method of quantifying how much support a hypothesis has from evidence consisting of data.

D. R. Bickel, “The strength of statistical evidence for composite hypotheses: Inference to the best explanation,” *Statistica Sinica* **22**, 1147-1198 (2012). Full article | 2010 version

The special law of likelihood has many advantages over more commonly used approaches to measuring the strength of statistical evidence. However, it only can measure the support of a hypothesis that corresponds to a single distribution. The proposed general law of likelihood also can measure the extent to which the data support a hypothesis that corresponds to multiple distributions. That is accomplished by formalizing inference to the best explanation.

## Frequentist inference principles

On some principles of statistical inference.

*Int. Stat. Rev.*83 (2015), no. 2, 293–308.

62A01 (62F05 62F15 62F25)

While agreeing with other frequentists on the necessity of guaranteeing good performance over repeated sampling, Reid and Cox also value neglected rules of inference such as the conditionality principle. Against the steady advance of nonparametric methods, Reid and Cox point to the interpretive power of parametric models.Frequentist decision theory is only mentioned. Glimpses of the authors’ perspectives on that appear in [D. R. Cox, Principles of statistical inference, Cambridge Univ. Press, Cambridge, 2006 (8.2); MR2278763 (2007g:62007)] and [N. M. Reid, Statist. Sci. 9 (1994), no. 3, 439–455; MR1325436 (95m:01020)].On the Bayes front, Reid and Cox highlight the success frequentist methods have enjoyed in scientific applications as a decisive victory over those Bayesian methods that are most consistent with their subjectivist foundations. Indeed, no one can deny what C. Howson and P. Urbach call the “social success” of frequentist methods [Scientific reasoning: the Bayesian approach, third edition, Open Court, Chicago, IL, 2005 (p. 9)]. Reid and Cox do not attribute their widespread use in scientific practice to political factors.

Rather, for scientific inference as opposed to individual decision making, they find frequentist methods more suitable in principle than fully Bayesian methods. For while the need for an agent to reach a decision recognizes no line between models of the phenomena under study and models of an agent’s thought, science requires clear reporting on the basis of the former without introducing biases from the latter. Although subjective considerations admittedly come into play in interpreting reports of statistical analyses, a dependence of the reports themselves on such considerations conflicts with scientific methodology. In short, the Bayesian theories supporting personal inference are irrelevant as far as science is concerned even if they are useful in personal decision making. This viewpoint stops short of that of Philip Stark, who went as far as to call the practicality of that private application of Bayesian inference into question [SIAM/ASA J. Uncertain. Quantif. 3 (2015), no. 1, 586–598; MR3372107].

On reference priors designed to minimize subjective input, Reid and Cox point out that those that perform well with low-dimensional parameters can fail in high dimensions. Eliminating the prior entirely leads to the pure likelihood approach, which, based on the strong likelihood principle, limits the scope even further, to problems with a scalar parameter of interest and no nuisance parameters [A. W. F. Edwards, Likelihood. An account of the statistical concept of likelihood and its application to scientific inference, Cambridge Univ. Press, London, 1972; MR0348869 (50 #1363)]. More recent developments of that approach were explained by R. M. Royall [Statistical evidence, Monogr. Statist. Appl. Probab., 71, Chapman & Hall, London, 1997; MR1629481 (99f:62012)] and C. A. Rohde [Introductory statistical inference with the likelihood function, Springer, Cham, 2014 (Chapter 18); MR3243684].

Reid and Cox see some utility in Bayesian methods that have good performance by frequentist standards, noting that such performance can require the prior to depend on which parameter happens to be of interest and, through model checking, on the data. Such dependence raises the question, “Is this, then, Bayesian? The prior distribution will then not represent prior knowledge of the parameter in [that] case, but an understanding of the model” [T. Schweder and N. L. Hjort, Scand. J. Statist. 29 (2002), no. 2, 309–332; MR1909788 (2003d:62085)].

Reviewed by David R. Bickel

This review first appeared at “On some principles of statistical inference” (Mathematical Reviews) and is used with permission from the American Mathematical Society.

## Coherent inference after checking a prior

D. R. Bickel, “Bayesian revision of a prior given prior-data conflict, expert opinion, or a similar insight: A large-deviation approach,” Working Paper, University of Ottawa, deposited in uO Research at http://hdl.handle.net/10393/34089/ (2015). 2015 preprint