Genetic algorithms, a class of nondeterministic algorithms in which the role of chance makes the precise nature of a solution impossible to guarantee, seem to be well suited to combinatorial-optimization problems in information retrieval. Provides an introduction to techniques and characteristics of genetic algorithms and illustrates their…

Discusses the relative effects of sample size and proportion in the use of sampling to investigate a population. Concludes that the nature of probability and statistics is such that in many situations, the reality is counterintuitive to many generally well-educated people who are not statistically trained. Discusses implications for educators.…

An integration of two different approaches to the psychology of causal induction is proposed that overcomes the problems associated with each. The proposal results in a causal power theory of the probabilistic contrast model of P. W. Cheng and L. R. Novick (1990). (SLD)

A FORTRAN subroutine is presented to calculate a generalized measure of agreement between multiple raters and a set of correct responses at any level of measurement and among multiple responses, along with the associated probability value, under the null hypothesis. (Author)

Examines query expansion during query translation in cross language information retrieval and develops a general framework for inferential information retrieval in two particular contexts: using fuzzy logic and probability theory. Obtains evaluation formulas that are shown to strongly correspond to those used in other information retrieval models.…

Presents an alternative approach to teaching Mendelian genetics that includes the use of mathematical procedures and models to describe the occurrence and probabilities of heritable outcomes. Examples illustrate use of the method to calculate genotypic and phenotypic ratios for crosses involving multiple alleles with independent and dependent…

Presents an overview of Rasch measurement models that begins with a conceptualization of continuous experiences often captured as discrete observations. Discusses the mathematical properties of the Rasch family of models that allow the transformation of discrete deterministic counts into continuous probabilistic abstractions. Also discusses six of…

Presents a model of tests and measurement that identifies test scores with Hilbert space vectors and true and error components of scores with linear operators. This geometric point of view brings to light relations among elementary concepts in test theory, including reliability, validity, and parallel tests. (Author/SLD)

This seventh in a series of articles discussing expert system construction focuses on two ways to create a structure that determines a decision: (1) rule-based, or deductive, implementation; and (2) example-based, or inductive, implementation. Probability factors and confidence levels are discussed, and an example is given for selecting an…

Discusses the probabilities and positive and negative predictive values of medical tests for HIV. (MKR)

Discussion of authorship distributions focuses on the results of a numerical study for fractional authorship attribution. Highlights include coauthors; multinomial coefficients; Lotka functions; probability distributions of articles per author; and probability distributions of authors per article. (LRW)

The phenomenon of 2 x 2 x 2 arrays having nonmaximal rank with positive probability, pointed out by J. Kruskal (1989), is generalized to 2 x "n" x "n" arrays. It is concluded that a pair of asymmetric square matrices can be diagonalized simultaneously with positive probability. (SLD)

Discussion of probabilistic information retrieval (IR) systems challenges the probability ranking principle in IR from the perspective of (1) signal detection-decision theory and (2) utility theory. Calibration, certainty, and independent assessment are discussed in terms of the relevance of documents, and standard retrieval policies are analyzed.…

The phimax adjustment to phi (Pearson's product moment correlation applied to binary data) is explored. Phi/phimax is shown to be a measure of relationship apart from its affiliation with phi. The relations between phi/phimax and kappa and limitations of phi/phimax are discussed. (SLD)

A model for preferential and triadic choice is derived in terms of weighted sums of central F distribution functions. It is a probabilistic generalization of Coombs' (1964) unfolding model from which special cases can be derived easily. This model for binary choice can be easily related to preference ratio judgments. (SLD)