The book can also be used as an excellent text for graduate-level courses in AI, operations research, or applied probability.

Proper linear models are those in which predictor variables are given weights such that the resulting linear composite optimally predicts some criterion of interest; examples of proper linear models are standard regression analysis, discriminant function analysis, and ridge regression analysis. Research summarized in P. Meehl's book on clinical vs statistical prediction and research stimulated in part by that book indicate that when a numerical criterion variable is to be predicted from numerical predictor variables, proper linear models outperform clinical intuition. Improper (...) linear models are those in which the weights of the predictor variables are obtained by some nonoptimal method. The present article presents evidence that even such improper linear models are superior to clinical intuition when predicting a numerical criterion from numerical predictors. In fact, unit weighting is quite robust for making such predictions. The application of unit weights to decide what bullet the Denver Police Department should use is described; some technical, psychological, and ethical resistances to using linear models in making social decisions are considered; and arguments that could weaken these resistances are presented. (shrink)

An examination of topics involved in statistical reasoning with imprecise probabilities. The book discusses assessment and elicitation, extensions, envelopes and decisions, the importance of imprecision, conditional previsions and coherent statistical models.

A review of the literature indicates that linear models are frequently used in situations in which decisions are made on the basis of multiple codable inputs. These models are sometimes used normatively to aid the decision maker, as a contrast with the decision maker in the clinical vs statistical controversy, to represent the decision maker "paramorphically" and to "bootstrap" the decision maker by replacing him with his representation. Examination of the contexts in which linear models have been successfully employed indicates (...) that the contexts have the following structural characteristics in common: each input variable has a conditionally monotone relationship with the output; there is error of measurement; and deviations from optimal weighting do not make much practical difference. These characteristics ensure the success of linear models, which are so appropriate in such contexts that random linear models may perform quite well. 4 examples involving the prediction of such codable output variables as GPA and psychiatric diagnosis are analyzed in detail. In all 4 examples, random linear models yield predictions that are superior to those of human judges. (shrink)

This paper uses the framework of Popper and Miller's work on axiom systems for conditional probabilities to explore Adams' thesis concerning the probabilities of conditionals. It is shown that even very weak axiom systems have only a very restricted set of models satisfying a natural generalisation of Adams' thesis, thereby casting severe doubt on the possibility of developing a non-Boolean semantics for conditionals consistent with it.

This text focuses on basic topics and problems of logic, as well as decision theory and topics related to the philosophy of science and statistics. Topics covered include inductive inference; causal inferrence; probability calculus; expected value; confirmation theory; the justification of induction; the riddle of induction and theories of probability. It also includes coverage, in both historical and contemporary terms, of the traditional problem of induction raised by Hume.