The Measurement of Statistical Evidence as the Basis for Statistical Reasoning
Open Access
- 17 November 2019
- conference paper
- conference paper
- Published by MDPI AG in Proceedings
- Vol. 46 (1), 7
- https://doi.org/10.3390/ecea-5-06682
Abstract
There are various approaches to the problem of how one is supposed to conduct a statistical analysis. Different analyses can lead to contradictory conclusions in some problems so this is not a satisfactory state of affairs. It seems that all approaches make reference to the evidence in the data concerning questions of interest as a justification for the methodology employed. It is fair to say, however, that none of the most commonly used methodologies is absolutely explicit about how statistical evidence is to be characterized and measured. We will discuss the general problem of statistical reasoning and the development of a theory for this that is based on being precise about statistical evidence. This will be shown to lead to the resolution of a number of problems.Keywords
This publication has 21 references indexed in Scilit:
- On the Jeffreys-Lindley ParadoxPhilosophy of Science, 2014
- Hypothesis Assessment and Inequalities for Bayes Factors and Relative Belief RatiosBayesian Analysis, 2013
- A limit result for the prior predictive applied to checking for prior-data conflictStatistics & Probability Letters, 2011
- Weak Informativity and the Information in One Prior Relative to AnotherStatistical Science, 2011
- Checking for prior-data conflictBayesian Analysis, 2006
- Optimally and computations for relative surprise inferencesThe Canadian Journal of Statistics / La Revue Canadienne de Statistique, 2006
- Testing Precise HypothesesStatistical Science, 1987
- Testing a Point Null Hypothesis: The Irreconcilability of P Values and EvidenceJournal of the American Statistical Association, 1987
- Sampling and Bayes' Inference in Scientific Modelling and RobustnessJournal of the Royal Statistical Society. Series A (General), 1980
- ConfirmationScientific American, 1973