Strong matching of frequentist and Bayesian parametric inference

49 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.

Probability matching priors (2004, background): “on the successive difierences of the observations. Fraser and Reid (2002) recently dis-”
Default priors for Bayesian and frequentist inference (2010, methodology): “In contrast the posterior survivor function for ρ under the flat prior dμ1 dμ2 is s.ρ/=Pr[ρ2 χ22{n.y21 +y22/}]: Numerical calculation confirms that there can be substantial undercoverage for right-hand tail intervals based on this marginal posterior (Fraser and Reid, 2002).”
Asymptotics and the theory of inference (2003, background): “Such priors are called strong matching priors in Fraser and Reid (2001) where it is shown that in most cases a usable solution does not emerge unless we consider matching only to O(n −1 ).”
Recent advances on Bayesian inference for $P(X < Y)$ (2011, background): “Following Fraser and Reid (2002), the prior π∗(R) is thus a ‘strong’ matching prior, in the sense that a frequentist p-value coincides with a Bayesian posterior survivor probability.”
On Some Principles of Statistical Inference (2015, background): “These priors are called strong matching priors by Fraser & Reid (2002).”