Abstract
A two-parameter generalization of Jaccard's index of similarity is proposed as a class of measures for testing the homogeneity of two independent multinomial samples. The power approach used in modern asymptotic theory of decomposable statistics is applied to the asymptotic analysis of these measures. The asymptotic analysis is amplified by numerical tabulation yielding an asymptotically optimal similarity test in this class of measures.
Similar content being viewed by others
References
P. Jaccard, “Nouvelles rechérches sur la distribution florale,”Bull. Soc. Vandoise des Sc. Nat.,144, 223–270 (1908).
W. P. McCormick, N. I. Lyons, and K. Hutcheson, “Distributional properties of Jaccard's index of similarity,”Comm. Statist. Theory Methods,121, No. 1, 51–68 (1992).
G. I. Ivchenko and S. A. Khonov, “On estimating the number of classes under censored data,” in:Statistical Methods of Estimation and Hypothesis Testing [in Russian], Perm' Univ. Press, Perm' (1993), pp. 52–57.
G.I. Ivchenko and V. V. Levin, “Asymptotic normality of a class of statistics in a polynomial scheme,”Teor. Veroyatnost. i Primenen. [Theory Probab. Appl.],21, No. 1, 190–195 (1976).
C. R. Rao,Linear Statistical Inference and its Applications, 2nd ed., Wiley, New York (1965).
Author information
Authors and Affiliations
Additional information
Translated fromMatematicheskie Zametki, Vol. 58, No. 4, pp. 536–546, October, 1995.
Rights and permissions
About this article
Cite this article
Ivchenko, G.I., Polepchuk, O.V. & Khonov, S.A. Concerning a class of similarity tests. Math Notes 58, 1049–1056 (1995). https://doi.org/10.1007/BF02305093
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02305093