Cambridge Dictionary of Statistics

Abstract

B.S. Everitt (1998) Pp. viii +359. Cambridge University Press, Cambridge. £19.95 (hardback), ISBN 0-521-59346-8. This book by B.S. Everitt contains 360 pages. It was first published by CUP in 1998. It is a 50% expansion of Everitt’s earlier successful dictionary, has an attractive layout and is reasonably priced. The aim of the book is to ‘provide students of statistics, working statisticians and researchers in many disciplines who are users of statistics with relatively concise definitions of statistical terms’. Most pages contain between eight and ten definitions. Some are accompanied by one or more formulae. This is a valuable reference book for all statisticians, and medical researchers who use and need to understand statistics. It is not essential for someone learning statistics for the first time as it refers to many advanced methods. Most definitions are followed by a reference which the reader can source for more details. There is a list of the most important reference sources at the beginning of the book. As well as definitions, the dictionary includes concise biographies of over 100 statisticians who have made major contributions to the subject. It also includes entries on the major statistical packages. Some entries are very short. For example, the entry for ‘non-orthogonal designs’ is ‘Analysis of variance designs with two or more factors in which the number of observations in each cell are not equal’. Others are longer and include equations. For example, the entry on ‘Least squares estimation’ includes 94 words, four equations and a reference. Many other entries include graphs. Up-to-date statistical methods are defined, mainly using medical examples, so that the non-medical reader will find much irrelevant material. Examples given range from the very elementary to advanced and they reflect the author’s background to such an extent that a better title may be The Cambridge Dictionary of Medical Statistics. Students of applied biology following a basic course in statistics will find most of the book difficult to understand, mainly because many of the definitions pertain to topics not covered in introductory courses. For non-mathematical students, even elementary definitions may cause problems. For example, for someone who does not know the meaning of the term standard deviation the explanation ‘The most commonly used measure of the spread of a set of observations. Equal to the square root of the variance’ would lead to ‘the second moment about the mean’ as the entry for variance. The definition given for moment may then result in further problems of understanding. However, to be fair to the author, he does give references to other texts. In particular, for more information on variance, standard deviation and many other elementary definitions the student is referred to Practical Statistics for Medical Research by D.G. Altman (1991), published by Chapman and Hall. Professional statisticians will find the dictionary a useful reference to statistical methods they may not yet be familiar with. It is particularly useful as a reference book for medical researchers when reading scientific papers. This book should be purchased by statisticians, libraries that support medical and veterinary departments, and research workers in medicine.