Treffer: Entropy, Statistical Evidence, and Scientific Inference: Evidence Functions in Theory and Applications.

Royall axiomatically based his evidential statistics on the law of likelihood [[11]] and the likelihood principle (LP) [[10]] and utilized the likelihood ratio (LR) as the canonical measure of statistical evidence. We should always admit the possibility that our experimental results may be best accounted for by a hypothesis which never entered our own heads. i (Barnard, 1949 page 136) We can broadly categorize Bayesians into three classes: subjective Bayesians, objective Bayesians, and empirical Bayesians. Some Bayesian statisticians and scientists fruitfully acknowledge these limitations and see Bayesian computation as an estimation device for complex models that needs to be followed by non-Bayesian calibration, confidence, and model-checking [[57]]. [Extracted from the article]