Calibration of ρ Values for Testing Precise Null Hypotheses

By T. Sellke, Maria J. Bayarri, James O. Berger. 2001

874 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/99a0ee68b45be3e72ebe9c9833f620ee77ee5d22

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Strengthening statistical usage in marine ecology (2012, background): “A solution to this staggering problem has been proposed, by reporting observed P‐values as lower bounds for Type 1 error probabilities (Sellke et al., 2001), but its complexity overshadows the actual tests originally performed.”
Bayesian evidence test for precise hypotheses (2003, neutral): “…Cox (1977), DeGroot (1970), Finetti (1974, 1981/1991), Gaskins (1992), Kokott (1998), Lauretto et al. (2002), Lindley (1957) (1978), Madruga et al. (2001), Pereira and Wechsler (1993), Pereira and Stern (1999a, b), Popper (1989), Savage (1962), Sellke et al. (1999), and Stern and Zacks (2002).”
Why P Values Are Not a Useful Measure of Evidence in Statistical Significance Testing (2008, methodology): “As reported in a number of studies (e.g., Berger, 2003; Hubbard & Bayarri, 2003a; and especially Sellke et al., 2001), a simulation of the frequentist performance of p values is revealing.”
E-values: Calibration, combination and applications (2019, neutral): “, Shafer [2019], who uses the term “betting score” in the sense very similar to our “e-value”, Shafer and Vovk [2019, Section 11.”
Objective Bayesian Methods for Model Selection: Introduction and Comparison (2001, background): “The chief limitation of this modified IBF approach is its considerable computational expense; thus, an FBF version of the analysis was also developed in Shui (1996). The key idea in this development was to notice that certain fractions of parts of the likelihood (with differing fractions for differe”
Default Bayes Factors for Model Selection in Regression (2012, result): “Of course, this inference yields results identical to the one-sample t test, and, consequently, inherits its poor calibration (Sellke, Bayarri, & Berger, 2001).”
The trim-and-fill method for publication bias: practical guidelines and recommendations based on a large database of meta-analyses (2019, background): “05([32])), because most statistical tests have low power to detect publication bias.”
Combining p-values via averaging (2012, neutral): “, [38]).”
AIC model selection and multimodel inference in behavioral ecology: some background, observations, and comparisons (2011, background): “People often want to " redefine " such P values to be the probability of the null, given the data—this is seriously wrong (see e.g. Sellke et al. 2001).”
Reconnecting p-Value and Posterior Probability Under One- and Two-Sided Tests (2018, background): “Sellke, Bayarri, and Berger (2001) proposed to calibrate p-value for testing precise null hypotheses.”
Admissible ways of merging p-values under arbitrary dependence (2020, positive): “In the experiments of Figure 3, we directly specify the distributions of p-values, under the alternative hypothesis, as a Beta(α, 1) distribution with density h(p) = αpα−1, p ∈ (0, 1), for some α ∈ (0, 1), suggested by Sellke et al. [2001]. A smaller value of α means a stronger evidence against the ”
Bayesian Adaptive Sampling for Variable Selection and Model Averaging (2011, methodology): “Under a posterior model of independence for the inclusion in- dicators γj , the size variables formed with the posterior marginal inclusion probabilities are perfectly correlated with the true posterior model probabilities.”
Valid P-Values Behave Exactly as They Should: Some Misleading Criticisms of P-Values and Their Resolution With S-Values (2019, background): “The latter interpretation is just a mistake (Goodman 1999; Sellke et al. 2001; Hubbard and Bayarri 2003; see also Greenland et al. 2016, item 9): The theory of α-level hypothesis tests requires an α 2 In parallel, P is conservatively valid if the rule “reject H when p ≤ α” will reject H with…”
Avoiding pitfalls when using information-theoretic methods (2002, background): “Shefferson et al. (2001) provide an excellent example of the use of QAICc and variance inflation in estimating dormancy in a rare orchid species.”