LikelihoodDr Edwards' stimulating and provocative book advances the thesis that the appropriate axiomatic basis for inductive inference is not that of probability, with its addition axiom, but rather likelihood - the concept introduced by Fisher as a measure of relative support amongst different hypotheses. Starting from the simplest considerations and assuming no more than a modest acquaintance with probability theory, the author sets out to reconstruct nothing less than a consistent theory of statistical inference in science. |
Contents
Bayes Theorem and inverse probability | 43 |
The Method of Support for several parameters | 103 |
Expected information and the distribution of evaluates | 144 |
Application in anomalous cases | 162 |
Support tests | 174 |
Miscellaneous topics | 199 |
Epilogue | 211 |
References | 219 |
Tables of support limits for t and x² | 225 |
Common terms and phrases
a₁ adopted alternative hypothesis application approximation arbitrary constant Bayes Bayesian best-supported value binomial boys chance set-up chapter concept defined estimation example expected information expected support function experimental fiducial argument figure Fisher formation matrix genotype given H₁ H₂ independent interpretation inverse probability Jeffreys Laplace Likelihood Axiom likelihood curve likelihood function Likelihood Principle likelihood ratio linear log-likelihood logarithm mathematical Maximum Likelihood mean Method of Maximum Method of Support millimetres Normal distribution nuisance parameter null hypothesis observed information matrix obtained particular population possible posterior posterior probability Principle of Indifference prior distribution prior probability prior support probability density probability distribution probability model probability statement problem proportion quadratic r₁ R₂ random relevance sample score simple solution statistical inference statistical model sufficient statistics support curve support equations support surface theorem theory tion transformation uniform variable variance vector zero σ²