Mean citation rate per article in mathematics journals: Differences from the scientific model

This paper analyzes the applicability of the article mean citation rate measures in the Science Citation Index Journal Citation Reports (SCI JCR) to the five JCR mathematical subject categories. These measures are the traditional 2-year impact factor as well as the recently added 5-year impact factor and 5-year article influence score. Utilizing the 2008 SCI JCR, the paper compares the probability distributions of the measures in the mathematical categories to the probability distribution of a scientific model of impact factor distribution. The scientific model distribution is highly skewed, conforming to the negative binomial type, with much of the variance due to the important role of review articles in science. In contrast, the three article mean citation rate measures' distributions in the mathematical categories conformed to either the binomial or Poisson, indicating a high degree of randomness. Seeking reasons for this, the paper analyzes the bibliometric structure of Mathematics, finding it a disjointed discipline of isolated subfields with a weak central core of journals, reduced review function, and long cited half-life placing most citations beyond the measures' time limits. These combine to reduce the measures' variance to one commensurate with random error. However, the measures were found capable of identifying important journals. Using data from surveys of the Louisiana State University (LSU) faculty, the paper finds a higher level of consensus among mathematicians and others on which are the important mathematics journals than the measures indicate, positing that much of the apparent randomness may be due to the measures' inapplicability to mathematical disciplines. Moreover, tests of the stability of impact factor ranks across a 5-year time span suggested that the proper model for Mathematics is the negative binomial. © 2010 Wiley Periodicals, Inc.

[1]  M. Greenwood,et al.  An Inquiry into the Nature of Frequency Distributions Representative of Multiple Happenings with Particular Reference to the Occurrence of Multiple Attacks of Disease or of Repeated Accidents , 1920 .

[2]  G. Pólya,et al.  Über die Statistik verketteter Vorgänge , 1923 .

[3]  The Relations between Stability and Homogeneity , 1931 .

[4]  Eugene Garfield,et al.  New factors in the evaluation of scientific literature through citation indexing , 1963 .

[5]  R. Merton.  The Matthew Effect in Science , 1968, Science.

[6]  E. Garfield.  Citation analysis as a tool in journal evaluation. , 1972, Science.

[7]  E. Garfield.  Significant journals of science , 1976, Nature.

[8]  Allan D. Pratt,et al.  A measure of class concentration in bibliometrics , 1977, J. Am. Soc. Inf. Sci..

[9]  Mark P. Carpenter.  Similarity of Pratt's measure of class concentration to the Gini index , 1979, J. Am. Soc. Inf. Sci..

[10]  Eugene Seneta,et al.  Bortkiewicz's Data and the Law of Small , 1987 .

[11]  G. Ross,et al.  Bortkewitsch's horse-kicks and the generalised linear model. , 1988 .

[12]  Per Ottar Seglen,et al.  How representative is the journal impact factor , 1992 .

[13]  Stephen J. Bensman.  The Structure of the Library Market for Scientific Journals: The Case of Chemistry , 1996 .

[14]  P. Seglen,et al.  Education and debate , 1999, The Ethics of Public Health.

[15]  Thed N. van Leeuwen,et al.  A new classification system to describe the ageing of scientific journals and their impact factors , 1998, J. Documentation.

[16]  Stephen J. Bensman,et al.  Scientific and Technical Serials Holdings Optimization in an Inefficient Market: A LSU Serials Redesign Project Exercise , 1998 .

[17]  Stephen J. Bensman.  Bradford's Law and Fuzzy Sets: Statistical Implications for Library Analyses , 2001 .

[18]  Alexander I. Pudovkin,et al.  Algorithmic procedure for finding semantically related journals , 2002, J. Assoc. Inf. Sci. Technol..

[19]  Alexander I. Pudovkin,et al.  Rank-normalized impact factor: A way to compare journal performance across subject categories , 2005, ASIST.

[20]  Peter Vinkler,et al.  Characterization of the impact of sets of scientific papers: The Garfield (impact) factor , 2004, J. Assoc. Inf. Sci. Technol..

[21]  Wolfgang Glänzel,et al.  A new classification scheme of science fields and subfields designed for scientometric evaluation purposes , 2004, Scientometrics.

[22]  E. Garfield.  The history and meaning of the journal impact factor. , 2006, JAMA.

[23]  Peter Vinkler,et al.  Ratio of short term and long term impact factors and similarities of chemistry journals represented by references , 1999, Scientometrics.

[24]  Stephen J. Bensman.  The impact factor, total citations, and better citation mouse traps: A commentary , 2007 .

[25]  Carl T. Bergstrom.  Eigenfactor Measuring the value and prestige of scholarly journals , 2007 .

[26]  Stephen J. Bensman.  Distributional differences of the impact factor in the sciences versus the social sciences: An analysis of the probabilistic structure of the 2005 journal citation reports , 2008 .

[27]  Carl T. Bergstrom,et al.  The Eigenfactor™ Metrics , 2008, The Journal of Neuroscience.

[28]  Marie E. McVeigh,et al.  The journal impact factor denominator: defining citable (counted) items. , 2009, JAMA.

[29]  Peter Vinkler.  Introducing the Current Contribution Index for characterizing the recent, relevant impact of journals , 2009, Scientometrics.

[30]  Stephen J. Bensman,et al.  Definition and identification of journals as bibliographic and subject entities: Librarianship versus ISI Journal Citation Reports methods and their effect on citation measures , 2009 .