ABS: Bensman, Probability distributions in library and information science: A historical and practitioner viewpoint
Gretchen Whitney
gwhitney at UTKUX.UTCC.UTK.EDU
Tue Oct 24 10:19:41 EDT 2000
Bensman SJ,
"Probability distributions in library and information science: A
historical and practitioner viewpoint" JOURNAL OF THE AMERICAN SOCIETY FOR
INFORMATION SCIENCE 51: (9) 816-833 JUL 2000
Author's e-mail: Stephen J. Bensman : notsjb at lsu.edu
EXCERPT FROM THE PAPER:
Final Considerations and a Practitioner Recommendation:
I will not discuss in this paper the debates provoked by the introduction of
the negative binomial into library and information science. This topic is
thoroughly covered in Bensman and Wilder (1998, pp.161-171). Here I only
want to emphasize three general conclusions, at which I arrived as a result
of research on the scientific information market and testing the National
Research Council database.
First, the skewed distributions found in library and information science and
described by empirical informetric laws are not unusual. The discovery of
these laws was only a part of a broad process of uncovering the skewed
distributions underlying phenomena in many other disciplines that took place
after Pearson's devastating assault on the normal paradigm. As a matter of
fact, the discovery of these skewed distributions was taking place even
before Pearson. For example, the doctrine of Karl Marx with its
concentration of the means of production and impoverishment of the masses
can be considered in many respects as the drawing of wrong conclusions from
a correct observation that the stochastic processes operative in the
negative binomial are operative in human society. In the paper in which he
derived the first informetric law-- the Inverse Square Law of Scientific
Productivity -- Lotka (1926) was well aware that he had found nothing
unusual. Thus, he wrote:
Frequency distributions of the general type (1) have a wide range of
applicability to a variety of phenomena, and the mere form of such a
ditribution throws little or no light on the underlying physical relations.
(p.323).
To back up these statements, Lotka cited the work of Corrado Gini on the
inequality of income within a population and John Christopher Willis on the
distribution of species. Perhaps the distinguishing feature of frequency
distributions within library and information science is the fuzzy nature of
the sets, within which they arise. This fuzziness is a function of the way
disciplines overlap and share the same literature. From this perspective,
the two most important informetric laws, which set apart library and
information science from other disciplines, are Bradford's Law of Scattering
and Garfield's Law of Concentration.
______________________________________________
TITLE : Probability distributions in library and information
science: A historical and practitioner viewpoint
AUTHOR Bensman SJ
JOURNAL JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE 51: (9)
816-833 JUL 2000
Document type: Article Language: English Cited References: 63
Times Cited: 0
Abstract:
This paper has a dual character dictated by its twofold purpose. First, it
is a speculative historiographic essay containing an
attempt to fix the present position of library and information science
within the context of the probabilistic revolution that has been
encompassing all of science. Second, it comprises a guide to practitioners
engaged in statistical research in library and information
science. There are pointed out the problems of utilizing statistical methods
in library and information science because of the highly
and positively skewed distributions that dominate this discipline.
Biostatistics are indicated as the source of solutions for these
problems, and the solutions are then traced back to the British biometric
revolution of 1865-1950, during the course of which
modern inferential statistics were created. The thesis is presented that
science has been undergoing a probabilistic revolution for
over 200 years, and it is stated that this revolution is now coming to
library and information science, as general stochastic models
replace specific, empirical informetric laws, An account is given of the
historical development of the counting distributions and
laws of error applicable in statistical research in library and information
science, and it is stressed that these distributions and laws
are not specific to library and information science but are inherent in all
biological and social phenomena, Urquhart's Law is used
to give a practical demonstration of the distributions. The difficulties of
precisely fitting data to theoretical probability models in
library and information science because of the inherent fuzziness of the
sets are discussed, and the paper concludes with the
description of a simple technique for identifying and dealing with the
skewed distributions in library and information science.
Throughout the paper, emphasis is placed on the relevance of research in
library and information science to social problems, both
past and present.
KeyWords Plus:
CIRCULATION MODEL, INFORMETRIC DISTRIBUTIONS, JOURNALS, MARKET, LAW
Addresses:
Bensman SJ, Louisiana State Univ, LSU Lib, Baton Rouge, LA 70803 USA.
Louisiana State Univ, LSU Lib, Baton Rouge, LA 70803 USA.
Publisher:
JOHN WILEY & SONS INC, NEW YORK
IDS Number:
324ZN
ISSN:
0002-8231
Cited Author Cited Work Volume
Page Year
PROBABILISTIC REVOLU
1987
BENSMAN SJ COLL RES LIBR 46 13
1985
BENSMAN SJ LIBR RESOUR TECH SER 42
147 1998
BENSMAN SJ LIBR RESOUR TECH SER 40
145 1996
BENSMAN SJ LIBRARY RES 4
279 1982
BOOKSTEIN A 5 INT C INT SOC SCI 73
1995
BOOKSTEIN A J AM SOC INFORM SCI 48 2
1997
BOOKSTEIN A J AM SOC INFORM SCI 41
368 1990
BOREL E PROBABILITIES LIFE
1962
BOREL E PROBABILITY CERTAINT
1963
BRADFORD SC ENGINEERING LONDON 137 85
1934
BROOKES BC INFORM PROCESS MANAG 20 37
1984
BROOKES BC J AM SOC INFORM SCI 30
233 1979
BROOKES BC J DOC 33
180 1977
BROWN R PSYCHOLOGY
1975
BURRELL QL J DOC 43
24 1987
BURRELL QL J DOC 42
114 1986
BURRELL QL J DOC 41
100 1985
BURRELL QL J ROY STAT SOC A STA 145 439
1982
COLEMAN JS INTRO MATH SOCIOLOGY
1964
CRATHORNE AR AM MATH MONTHLY 35 169
1928
EHRENBERG ASC APPL STAT 3
26 1959
ELLIOTT JM FRESHWATER BIOL ASS 25
1977
FELLER W ANN MATH STAT 14 389
1943
FRASER S BELL CURVE WARS RACE
1995
FUSSLER HH PATTERNS USE BOOKS L
1969
GALTON F HEREDITARY GENIUS IN
1978
GALTON F INQUIRIES HUMAN FACU
1883
GALTON F NATURAL INHERITANCE
1889
GALTON F P R SOC 29
365 1879
GARFIELD E CURR CONTENTS 3
5 1971
GARFIELD E SCIENCE 178
471 1972
GREENWOOD M J R STATIST SOC 83 255
1920
HERRNSTEIN RJ BELL CURVE INTELLIGE
1994
HOGBEN L STAT THEORY RELATION
KEYNES JM TREATISE PROBABILITY
1921
LOTKA AJ J WASHINGTON ACADEMY 16
317 1926
MACKENZIE DA STAT BRITAIN 1865 19
1981
MCALISTER D P R SOC LONDON 29 367
1879
NEWBOLD E J R STATIST SOC 90 487
1927
NEYMAN J ANN MATH STATISTICS 10 35
1939
PEARSON ES STUDIES HIST STAT PR 1 323
1970
PEARSON K BIOMETRIKA 11
139 1915
PEARSON K K PEARSONS EARLY STA
1 1956
PEARSON K K PEARSONS EARLY STA 41
1956
PEARSON K K PEARSONS EARLY STA 339
1956
PEARSON K K PEARSONS EARLY STA 529
1956
PEARSON KR BIOMETRIKA 4 169
1905
PRICE DDS J AM SOC INFORM SCI 27 292
1976
SARNDAL CE STUDIES HIST STAT PR 2 419
1977
SHOCKLEY W P IRE 45
279 1957
SNEDECOR GW STAT METHODS
1989
STIGLER SM HIST STAT MEASUREMEN
1986
STIGLER SM STAT PROBABILITY LET 1 32
1982
THORNDIKE F BELL SYST TECH J 5 604
1926
TRUESWELL R WILSON LIBRARY B 43 458
1969
URQUHART DJ J DOC 15
21 1959
URQUHART DJ P 1
287 1959
URQUHART DJ PRINCIPLES LIB
1981
WELDON WFR P ROYAL SOC LONDON 54 318
1893
WESTERGAARD H CONTRIBUTIONS HIST S
1968
WINSOR CP HUMAN BIOL 19 154
1947
YULE GU J ROY STATIST SOC 73 26
1910
-------------------------------------------------------------
(c) ISI, Reprinted with permission
Please visit their website at www.isinet.com
More information about the SIGMETRICS
mailing list