Search results
1 – 10 of over 7000Bradford distributions describe the relationship between ‘journal productivities’ and ‘journal rankings by productivity’. However, different ranking conventions exist, implying…
Abstract
Bradford distributions describe the relationship between ‘journal productivities’ and ‘journal rankings by productivity’. However, different ranking conventions exist, implying some ambiguity as to what the Bradford distribution ‘is’. A need accordingly arises for a standard ranking convention to assist comparisons between empirical data, and also comparisons between empirical data and theoretical models. Five ranking conventions are described including the one used originally by Bradford, along with suggested distinctions between ‘Bradford data set’, ‘Bradford distribution’, ‘Bradford graph’, ‘Bradford log graph’, ‘Bradford model’ and ‘Bradford’s Law‘. Constructions such as the Lotka distribution, Groos droop (generalised to accommodate growth as well as fall‐off in the Bradford log graph), Brookes hooks, and the slope and intercept of the Bradford log graph are clarified on this basis. Concepts or procedures questioned include: (1) ‘core journal’, from the Bradfordian viewpoint; (2) the use of traditional statistical inferential procedures applied to Bradford data; and (3) R(n) as a maximum (rather than median or mean) value at tied‐rank values.
Details
Keywords
M. Carl Drott, Jacqueline C. Mancall and Belver C. Griffith
Bradford's Law is presented as an observation made from the outcome of searching, rather than a mathematical development. The organization and presentation of search data is…
Abstract
Bradford's Law is presented as an observation made from the outcome of searching, rather than a mathematical development. The organization and presentation of search data is explained. Potential applications of Bradford's Law are discussed. New findings are presented which show the relationship described by Bradford's Law to be fundamentally important but in a more subtle way than previously supposed. Future developments are suggested in terms of their impact on librarianship.
The Bradford law is explored theoretically by means of a very mixed Poisson model which, it is claimed, elucidates the uncertainties surrounding the law and its applications. It…
Abstract
The Bradford law is explored theoretically by means of a very mixed Poisson model which, it is claimed, elucidates the uncertainties surrounding the law and its applications. It is argued that Bradford succeeded in formulating an empirical regularity which has pure and hybrid forms but that all the variants can be subsumed under a simple logarithmic law which, for reasons explained, escapes exact expression in conventional frequency terms. The theoretical aspects discussed include the hybridity of form, estimations, sampling problems, the stability of ranks, homogeneity of data, and tests of significance. Some numerical examples, some simulated and some drawn from social contexts outside bibliography, are used both to illustrate theoretical issues and also to indicate the wide generality of the Bradford law. Possible applications and developments of the theory are indicated.
Haitun has recently shown that empirical distributions are of two types—‘Gaussian’ and ‘Zipfian’—characterized by the presence or absence of moments. Gaussian‐type distributions…
Abstract
Haitun has recently shown that empirical distributions are of two types—‘Gaussian’ and ‘Zipfian’—characterized by the presence or absence of moments. Gaussian‐type distributions arise only in physical contexts: Zipfian only in social contexts. As the whole of modern statistical theory is based on Gaussian distributions, Haitun thus shows that its application to social statistics, including cognitive statistics, is ‘inadmissible’. A new statistical theory based on ‘Zipfian’ distributions is therefore needed for the social sciences. Laplace's notorious ‘law of succession’, which has evaded derivation by classical probability theory, is shown to be the ‘Zipfian’ frequency analogue of the Bradford law. It is argued that these two laws together provide the most convenient analytical instruments for the exploration of social science data. Some implications of these findings for the quantitative analysis of information systems are briefly discussed.
It is argued that the powerful techniques of OR operate on only a small fraction of the statistical information that the social sciences usually provide. This argument is…
Abstract
It is argued that the powerful techniques of OR operate on only a small fraction of the statistical information that the social sciences usually provide. This argument is illustrated by Leimkuhler's recent claim to have found an ‘exact’ fit to the Bradford law. An elementary theorem of Shannon information theory shows that his new function is applied to only 2·3% of the statistical information inherent in the bibliography he chooses and that Bradford's original simple formulation not only fits this segment but also the whole bibliography more closely than the new formulation. As every loss of statistical information can be measured, it can be shown that sophisticated mathematical techniques cannot compensate for the information they squander.
A probabilistic mechanism is proposed to describe various forms of the Bradford phenomenon reported in bibliometric research. This leads to a stochastic process termed the Waring…
Abstract
A probabilistic mechanism is proposed to describe various forms of the Bradford phenomenon reported in bibliometric research. This leads to a stochastic process termed the Waring process, a special case of which seems to conform with the general features of ‘Bradford's Law’. The presence of a time parameter in the model emphasises that we are considering dynamic systems and allows the possibility of predictions being made.
An exact, discrete formulation of Bradford's law describing the distribution of articles in journals is derived by showing that Bradford's law is a special case of the…
Abstract
An exact, discrete formulation of Bradford's law describing the distribution of articles in journals is derived by showing that Bradford's law is a special case of the Zipf‐Mandelbrot ‘rank frequency’ law. A relatively simple method is presented for fitting the model to empirical data and estimating the number of journals and articles in a subject collection. This method is demonstrated with an example application.
Any statistical regularities found in documentation should be fully exploited to produce estimates or predictions and to save documentalists work. But present formulations of the…
Abstract
Any statistical regularities found in documentation should be fully exploited to produce estimates or predictions and to save documentalists work. But present formulations of the Bradford distribution demand penetrating search for peripheral papers and tedious computation in application. The present paper shows that the Bradford distribution is closely related to the Zipf distribution. It requires data on only the most productive journals, is mathematically simple and amenable to graphical methods if a proposed idea of the ‘completeness’ of a search is accepted. For comparability of results, certain conditions, which include a specified minimum level of productivity of journals, need to be standardized. A standard form is suggested. It is found, however, that a modified form of the Bradford distribution is required when Bradford‐type collections of journals are merged into larger collections, when ‘saturation’ of the most productive journals occurs.
The distribution of references in a collection of pertinent source documents can be described and predicted by the relation where the parameter ß is related to the subject field…
Abstract
The distribution of references in a collection of pertinent source documents can be described and predicted by the relation where the parameter ß is related to the subject field and the completeness of the collection. The model is used to predict the reference yield of abstracting journals in a search for thermophysical property data. It is used also to explain differences among various literature studies of the past in terms of differences in subject and comprehensiveness of search. The model is derived from S. C. Bradford's ‘law of scattering’ and is called the Bradford Distribution.
BY the sudden death of Dr. Samuel Clement Bradford on 13 November 1948 British documentation has lost another of its outstanding personalities. It is a sad coincidence that in two…
Abstract
BY the sudden death of Dr. Samuel Clement Bradford on 13 November 1948 British documentation has lost another of its outstanding personalities. It is a sad coincidence that in two successive issues of the Journal of Documentation we should have been obliged to record the loss of Dr. Bradford and Professor A. F. C. Pollard.