Swets' theory of information retrieval allows the threads of document weighting formulae, probabilistic measures of effectiveness, and management theory, to be woven into a coherent pattern. Benefits are: the beginnings of a quantitative description of retrieval languages; destinction between retrieval systems and language; and question generality…

Confirms previously published research in concluding that specialty words tend to possess frequency distributions which cannot be described by a single Poisson distribution. (Author/PF)

Examines statistical techniques for exploiting relevance information to weight search terms. These techniques are presented as a natural extension of weighting methods using information about the distribution of index terms in documents in general. (Author)

Discusses a reliability theoretic construct focusing on information produced to satisfy specified purposes or achieve preconceived objectives. When measures of system reliability and sensitivity analyses are performed, the result is a closer congruence between the objectives of the data producer and user requirements. (Author/MBR)

Describes a procedure for information retrieval testing that is based on the comparison of statistically independent methods of retrieval applied to the same database. The probability ranking principle is discussed, the statistical meaning of relevance is examined, and the methodology is illustrated on a large database of MEDLINE records. (19…

Proves price index (proportion of references within the last five years of literature) is not a pure function of the mean or median reference age, but a well-defined relation in the form of a typical cloud of points. Compares models for analyzing price index (decreasing exponential and lognormal aging) and explains cloud using results from…

Uses bibliometric techniques in the development of a model of the distribution of demand for items in an information store. The hypothesis of hyperbolic distribution and an index of differential demand are also discussed. One table, two figures, and a 10-item reference list accompany the text. (Author/JL)

Introduces two data distortion methods (Frequency-Imposed Distortion, Frequency-Imposed Probability Distortion) and uses a Monte Carlo study to compare their performance with that of other distortion methods (Point Distortion, Probability Distortion). Indications that data generated by these two methods produce accurate statistics and protect…