I. J. Good
YOU?
Author Swipe
Limited Competition Open
In my article (Good, 1967, p. 90), I said "The more the program is based on the methods used by humans the more light it will shed on the nature of thought processes.But for the sake of a clear-cut objective I should like to write a progra…
Corrigenda Volume 37 (1941), 199-228 Open
An abstract is not available for this content so a preview has been provided. As you have access to this content, a full PDF is available via the ‘Save PDF’ action button.
Diagnosis of acute myocardial infarction from two measurements of creatine kinase isoenzyme MB with use of nonparametric probability estimation. Open
By using bivariate probability estimation for the diagnosis of acute myocardial infarction (AMI) we show how to overcome the difficulties encountered for patients whose clinical presentation is atypical and those encountered when multiple …
Fide’s Objection Refuted Open
The Editors have recently received a communication from Derek Oldbury, who was Checkers World Champion 1976Champion -1982. .In it, he takes issue with the Editorial Statement as published in Three Generations Meet- ing (Vol.9, No.1, p. 2) …
The Interface Between Statistics and Philosophy of Science Open
Many points of contact between statistics and the philosophy of science are reviewed. Some of the topics mentioned are kinds of probability, weight of evidence (corroboration), tail probabilities ($p$-values), Bayes/non-Bayes compromises, …
The Amalgamation and Geometry of Two-by-Two Contingency Tables Open
If a pair of two-by-two contingency tables are amalgamated by addition it can happen that a measure of association for the amalgamated table lies outside the interval between the association measures of the individual tables. We call this …
The Robustness and Sensitivity of the Mixed-Dirichlet Bayesian Test for "Independence" in Contingency Tables Open
A mixed-Dirichlet prior was previously used to model the hypotheses of "independence" and "dependence" in contingency tables, thus leading to a Bayesian test for independence. Each Dirichlet has a main hyperparameter $\\kappa$ and the mixi…
Some Statistical Applications of Poisson's Work Open
Statistical applications and repercussions of Poisson's work are reviewed in historical perspective with special reference to (i) the distinction he made between two kinds of probability; (ii) the law of large numbers; (iii) the Poisson di…
Variation in periodontal floras Open
Statistical analyses indicated (i) that the floras of individual samples taken from the depth of sulci with nickel-plated Morse 00 scalers were highly reproducible and representative of the flora present at any given time, (ii) that the di…
Bacteriology of experimental gingivitis in young adult humans Open
From replicate trials of experimental gingivitis in four periodontally healthy subjects, 166 bacterial species and subspecies were detected among 3,034 randomly selected isolates from 96 samples. Of these bacteria, Actinomyces naeslundii (…
On the Application of Symmetric Dirichlet Distributions and Their Mixtures to Contingency Tables, Part II Open
This paper is a continuation of a paper in the Annals of Statistics (1976), 4 1159-1189 where, among other things, a Bayesian approach to testing independence in contingency tables was developed. Our first purpose now, after allowing for a…
Bayesian non-parametric theory: discussion Open
A 60-year-old man was admitted at his local hospital for persistent chest pain and suspicion of aortic dissection. No evidence of aortic dissection or intimal disruption was noted by means of computed tomography and transesophageal echocar…
A New Formula for $k$-Statistics Open
A new formula for cumulants was given by Good (1975). A short proof is now given and the result is used to obtain a new formula for $k$-statistics. This formula can be used both for deriving the expressions of $k$-statistics in terms of po…
On the Application of Symmetric Dirichlet Distributions and their Mixtures to Contingency Tables Open
Bayes factors against various hypotheses of independence are proposed for contingency tables and for multidimensional contingency tables. The priors assumed for the nonnull hypothesis are linear combinations of symmetric Dirichlet distribu…