A CIRCULATION MODEL FOR BUSY PUBLIC LIBRARIES
| Pages | 24-37 |
| Date | 01 January 1983 |
| Published date | 01 January 1983 |
| DOI | https://doi.org/10.1108/eb026737 |
| Author | A. BAGUST |
| Subject Matter | Information & knowledge management,Library & information science |
A CIRCULATION MODEL FOR BUSY PUBLIC LIBRARIES
A. BAGUST
Finance Department, Kirklees Metropolitan Council
Starting from a basis laid by Burrell, this paper develops a stochastic model of
library borrowing using the Negative Binomial distribution. This shows an im-
provement over previous characterizations for academic libraries and accords well
with new data obtained at Huddersfield Public Library. Evidence concerning the
process of issue decay is presented and employed to obtain an optimum stock turn-
over rate for any collection in its 'steady state'. A method is then given by which
simple relegation tests can be constructed to maintain such
as
optimum turnover.
Although not the 'final word' in circulation modelling, the negative binomial
distribution extends the range of model applicability into the area of high volume,
rapid movement collections with some success.
1.
INTRODUCTION
IN PROPOSING
A
SIMPLE STOCHASTIC MODEL for library
loans,
Burrell1
employed a geometric distribution for circulation data, using data from three
academic libraries to illustrate his model. Hindle and Worthington2 demon-
strated that the geometric distribution was only one of
a
range of possible statis-
tical descriptions of the data, some of which can be in better accord with the data
used by Burrell. However, the alternative model of Hindle and Worthington is
not presented as a serious contender, being merely illustrative of the weakness of
Burrell's reasoning. A further element in the debate has been provided by Wall3
who suggested that negative binomial distributions might give better approxima-
tions to available data.
Burrell's more recent paper7 concedes the limitations of
his
model and examines
the possible use of other statistical distributions, including negative binomial,
whilst still defending his original proposal
as
'worth considering
as a
first approxi-
mation'.
To date this debate has centred upon information from academic libraries,
where average usage is necessarily low. For general applicability, models should
also be viable for busy public libraries with far greater borrowing rates. Circula-
tion data derived from Huddersfield Public Library clearly exposed the inadequacy
of Burrell's original model, and led to the development of Wall's suggestion as a
viable alternative.
2. MODELLING: A CRITIQUE OF BURRELL'S MODELS
Burrell's models of library circulation rest on three propositions:7
(i) That the times of borrowings of an item form a Poisson process.
(ii) That the 'desirability' of items within a collection are governed by a given
probability distribution (originally negative exponential).
(iii) That any collection will contain
a
class of items which are essentially 'dead' in
terms of circulation (the zero class).
Journal
of
Documentation,
Vol. 39, No. 1, March 1983, pp. 24–37.
24
To continue reading
Request your trial