The Statistical Education of Harold Jeffreys
نویسندگان
چکیده
The paper considers the statistical work of the physicist Harold Jeffreys. In 1933–4 Jeffreys had a controversy with R.A. Fisher, the leading statistician of the time. Prior to the encounter, Jeffreys had worked on probability as the basis for scientific inference and had used methods from the theory of errors in astronomy and seismology. He had also started to rework the theory of errors on the basis of his theory of probability. After the encounter Jeffreys produced a full-scale Bayesian treatment of statistics in the form of his Theory of Probability.
منابع مشابه
Invariance of Posterior Distributions under Reparametrization
In 1946, Sir Harold Jeffreys introduced a prior distribution whose density is the square root of the determinant of Fisher information. The motivation for suggesting this prior distribution is that the method results in a posterior that is invariant under reparametrization. For invariant statistical models when there is a transitive group action on the parameter space, it is shown that all rela...
متن کاملCould Fisher, Jeffreys and Neyman Have Agreed on Testing?
Ronald Fisher advocated testing using p-values, Harold Jeffreys proposed use of objective posterior probabilities of hypotheses and Jerzy Neyman recommended testing with fixed error probabilities. Each was quite critical of the other approaches. Most troubling for statistics and science is that the three approaches can lead to quite different practical conclusions. This article focuses on discu...
متن کاملThe Philosophy and Functions of Verbal Violence in Harold Pinter’s Mountain Language: A CDA Approach
The present study considers the issue of verbal violence in the language of drama. In the evaluation of verbal violence, Jeanette Malkin (2004) proposes six maxims, through which language may be considered as an arrogant element. The characters in dramatic texts (as in other literary texts) are created, developed, evolved and - in some cases - destroyed by language. In a considerable numb...
متن کاملLocation Reparameterization and Default Priors for Statistical Analysis
This paper develops default priors for Bayesian analysis that reproduce familiar frequentist and Bayesian analyses for models that are exponential or location. For the vector parameter case there is an information adjustment that avoids the Bayesian marginalization paradoxes and properly targets the prior on the parameter of interest thus adjusting for any complicating nonlinearity the details ...
متن کاملThe differential prior gives second order inference for scalar and vector parameters
Jeffreys (1946) proposed a root-information prior for the likelihood analysis of a statistical model. Then for an exponential model with scalar parameter Welch & Peers (1963) showed that this leads to second-order inference, or more specifically that posterior intervals have second order confidence. But for an exponential model with vector-parameter Jeffreys (1961) found that the root informati...
متن کامل