On the Probability of Observing Misleading Statistical Evidence

By R. Royall. 2000

239 citations recorded by the source corpus.

How researchers see this paper

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

NFI-FRITS: A forensic speaker recognition database and some first experiments (2014, background): “Sometimes the proportion of non-target trials with ` > 0 is referred to as the ‘misleading evidence’ [26], but of course for calibrated ` this is just the equal error rate E=.”
Bayes factor design analysis: Planning for compelling evidence (2016, background): “and the probability of misleading evidence are conceptually distinct, but practically tightly related properties of a research design (Royall, 2000), as in general higher evidential thresholds will lead to lower rates of misleading evidence (Blume, 2008; Schönbrodt et al.”
Safe Testing (2019, background): “For such s-values that are really simple-H0-based Bayes factors, Proposition 1 reduced to the well-known universal bound for likelihood ratios that has been rediscovered many times (see Royall (2000) for an overview).”
Interpreting statistical evidence by using imperfect models: robust adjusted likelihood functions (2003, background): “…samples the probability ofmisleading evidence,P{L.θ/=L.θ0/ k}, as a function of θ, is approximated by the bump function, Φ{−c=2 − ln.k/=c}, where k is any constant greater than 1, Φ is the standard normal distribution function and c is proportional to the distance between θ and θ0 (Royall, 2000).”