Developments in bibliometrics

Haitun has shown the laws of bibliometrics to be a peculiar family of statistical distributions (the Zipfian family) that is apparently beyond the reach of orthodox statistical theory -- the Gaussian family of distributions. Sichel describes further developments concerning the distribution he derive...

Full description

Saved in:
Bibliographic Details
Published in:Journal of information science 1985-01, Vol.10 (2), p.91-92
Main Author: Brookes, B.C.
Format: Article
Language:English
Subjects:
Bibliometrics
Distribution
Mathematical analysis
Probability
Statistical methods
Theory
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Haitun has shown the laws of bibliometrics to be a peculiar family of statistical distributions (the Zipfian family) that is apparently beyond the reach of orthodox statistical theory -- the Gaussian family of distributions. Sichel describes further developments concerning the distribution he derived and applied to vocabulary distributions; it appears, then, that Haitun's Zipfian distributions can be derived from classical probability theory, after all. The ''inverse Gaussian'' distribution is related to diffusion processes. By imposing a further random process, Sichel obtains the general inverse-Gaussian-Poisson distribution (IGPD), which can be expressed only in terms of Bessel functions. Haitun's dichotomy distinguishing the distributions remains valid, but the Zipfian family would now be better named ''Inverse Gaussian.'' Confident applications to the social sciences probably will require programming of an appropriate statistical package.
ISSN:0165-5515
1741-6485
DOI:10.1177/016555158501000206