There has been a considerable growth of interest in the potential which is offered by the relatively new techniques of social network analysis. Unfortunately, this potential has been seen as unachievable for many researchers, who have found it difficult to come to grips with the highly technical and mathematical language in which much discussion of these techniques has been cast. Those who have wanted to take advantage of the techniques of social network analysis have been practical researchers with substantive interests, while texts and sources on these techniques have, by and large, been produced by highly numerate specialists with a mathematical background. There has even been great difficulty in finding out about the available computer programs for social network analysis; and when access to a program has been achieved, researchers often have little practical guidance on its uses and applications.
My aim in this book is to try to bridge this gap between theory and practice. I am not a specialist with a mathematical training, but a researcher who came to social network analysis because of the particular needs of data handling in a research project on corporate power. Over the years, I have struggled to achieve a degree of understanding of what the principal measures of network structure involve, and I have attempted to translate the mathematics into simpler language and to try to assess the relevance of particular models for specific research needs. The aim of the book, therefore, is to draw on this experience in order to present a systematic summary of these measures with some illustrations of their uses. I have not attempted to present a comprehensive treatise on structural analysis in sociology (see Berkowitz, 1982), nor have I aimed at reviewing the large number of applications of social network analysis which have been published (see Mizruchi and Schwartz, 1987; Wellman and Berkowitz, 1988). 1 have concentrated on identifying the key concepts used in assessing network structure density, centrality, cliques and so on - and I have tried to translate the mathematical discussions of these ideas into more comprehensible terms.
It is of the utmost importance that researchers understand the concepts that they use. There are, for example, a large number of
2 Social network analysis
different definitions of the 'clique' and of related ideas, and a researcher cannot simply take a program 'off the shelf' and assume that its idea of the clique corresponds with that which the researcher has in mind. It is for this reason that I emphasize, at a number of points, that the choice of measures and of their application to particular topics are matters that require the informed judgement of the practising researcher. They are theoretical and empirical questions which cannot be avoided by a reliance on mathematical measures that are only partly, if at all, understood. Only if the researcher has a clear understanding of the logic of a particular measure can he or she make an informed sociological judgement about its relevance for a particular piece of research.