Probability Distributions > Bradford distribution
The Bradford distribution is a special type of right-skewed curve, first uncovered in 1949 by S.C. Bradford when he used it to explain how diverse information on a certain topic can be found across various sources and references – instead of being haphazardly scattered, the data follows an archetypal pattern. This unique law sheds light into where people might look for specific types of details relating to any number of topics or subjects.
Bradford’s law of scattering is a special case of the beta distribution of the second kind or Pearson’s Type VI. It is similar in shape to a right-truncated Pareto distribution.
PDF for the Bradford Distribution
The probability density function is:
Where x is a proportion.
Real Life Example of the Bradford Distribution
The distribution was first described by Bradford in 1934 [1] and then in detail, again by Bradford, in 1948 [2], when he used it to show how sources are distributed in the field of documentation. It shows how information about a particular subject is scattered throughout various references, where the information is likely to be found. The information isn’t randomly scattered, but rather follows a characteristic pattern [3].
Bradford found that a small number of popular journals contained as many papers on a particular topic as a larger number of papers (n), which in turn contains as many papers as an even larger number of papers, n2. In other words, if journals are arranged in order of decreasing productivity of articles on a given subject, they can be divided into a core of journals devoted to the subject with radiating zones of journals contributing fewer and fewer articles [4].
The exact numbers depend on the topic being studied. But let’s say you were studying how often articles on the topic of “bariatric surgery” showed up in journals. You might find that the top 10 journals had 20 articles on bariatric surgery in the last year. Another 50 less popular journals might also have 20 articles on that topic, while the remaining journals (say, 200) also have the same number of articles (20). Thus, articles of interest tend to be clustered towards a core group of journals.
This application is called “bradfordization” and explains the differences among subject and comprehensiveness of search in historical literature studies.
References
- Bradford, S. C. 1934. “Sources of information on specific subjects.” Engineering 137 (3550): 85-86. [Reprint, Journal Information Science, 1985, 10: 176-180]
- S. C. Bradford, “The Documentary Chaos,” in Documentation (London: Lockwood, 1948), 144–159.
- Fidel, R. (2002). CoLIS 4: Proceedings of the Fourth International Conference on Conceptions of Library and Information Science, Seattle, WA, USA, July 21-25, 2002.
- Davis, P. Where to Spend our E-journal Money? Defining a University Library’s Core Collection Through Citation Analysis.