Similarity of Binary Data

Abstract

<it>Baroni-Urbani, C. (Natural History Museum, Augustinergasse 2, CH-4051 Basel, Switzerland), and Buser, M. W. (Department of Nuclear Physics,<cross-ref type="fn" refid="fn1">2</cross-ref> Klingelbergstrasse 82, and Computing Center, Klingelbergstrasse 70, University of Basle, CH-4000 Basel, Switzerland) 1976. Similarity of binary data. Syst. Zool. 25:251–259</it>.—A set of intuitively obvious properties of a coefficient of similarity for binary data is established. Critical examination of the coefficients available from the literature shows that none of them satisfies all these properties, and a new coefficient is proposed to obviate this inconvenience. The distribution of the new coefficient is studied on very large, perfectly random samples of OTU'S, and a table is constructed to show its critical values at different significance levels. A mathematical appendix is given to demonstrate the procedure used to construct perfectly random samples of different size.