Technical Note—Exact Solution for the Bradford Distribution and Its Use in Modeling Informational Data

Abstract

Please scroll down for article-it is on subsequent pages With 12,500 members from nearly 90 countries, INFORMS is the largest international association of operations research (O.R.) and analytics professionals and students. INFORMS provides unique networking and learning opportunities for individual professionals, and organizations of all types and sizes, to better understand and use O.R. and analytics tools and methods to transform strategic visions and achieve better outcomes. For more information on INFORMS, its publications, membership, or meetings visit http://www.informs.org

Characterising program behaviour with phases and transitions

“…A locality curve is designed to reflect both the concentration aspect of locality as well as the aspect of persistence. The measure of locality, L, stems from the Bradford-Zipf distribution and its properties, most specifically a measure of "concentration of productivity" first proposed by Morse and Leimkuhler [1979] and adapted by Bunt and Murphy [1984] to the context of program behaviour. The curve plots the measure of locality as a function of Locality curves were also produced for I references and D references separately.…”

Bradford's distribution: From the classical bibliometric ?law? to the more general stochastic models

“…The above discussed ambiguities induced, in addition, strong empirical evidence, nor theoretical rationale to support it. Despite the early evidence of the inflection in the different formulations of Bradford's distribution, with the aim of providing a better curve fit (Brookes, 1968(Brookes, , 1969; upper tail (S-shaped curve), first noted by Groos (1967), and the fact that it appears too often to allow one to treat Haspers, 1976;Leimkuhler, 1967Leimkuhler, , 1980Maia & Maia, 1984;Morse, 1981a;Morse & Leimkuhler, 1979; Praunit as an isolated phenomenon, the J-shaped curve has been anticipated in most experimental as well as theoretical lich & Kroll, 1978;Vickery, 1948;Wilkinson, 1972). For a comprehensive review of theoretical models of approaches.…”

Implications of the exact bradford distribution

“…The appropriate response, of course, is to utilize mathematical techniques to obtain an exact solution, complying exactly with the Bradford requirement relating cumulative numbers of journals and cumulative production, keeping in mind that n is a discrete, not a continuous, variable. This has recently been done [7] and the results show that the data in many cases fit the exact solution better than they do the approximate one; in fact, the fit is satisfactory even for the periodicals publishing only one article in the specialty per year.…”

“…Details of their derivation have been given in anearlier paper 6 . Only a few of these properties are needed for our discussion here.…”