Measures of distance between probability distributions. (English) Zbl 0669.60025

Distances between probability distributions are characterized by functional equations of the following types: \[ f(pr,qs)+f(ps,qr)=(r+s)f(p,q)+(p+q)f(r,s)\quad and\quad f(pr,qs)+f(ps,qr)=f(p,q)f(r,s). \] Special cases are the Hellinger coefficient, Jeffreys distance, Chernoff coefficient, J-divergence, etc.
Reviewer: J.Székely


60E05 Probability distributions: general theory
39B99 Functional equations and inequalities
Full Text: DOI


[1] Aczél, J, Lectures on functional equations and their applications, (1966), Academic Press New York/London · Zbl 0139.09301
[2] Aczél, J; Baker, J.A; Djoković, D.Z; Kannappan, Pl; Radó, F, Extensions of certain homomorphisms of subsemigroups to homomorphisms of groups, Aequationes math., 6, 263-271, (1971) · Zbl 0224.20036
[3] Aczél, J; Ng, C.T; Wagner, C, Aggregation theorems for allocation problems, SIAM J. algebraic discrete methods, 5, 1-8, (1984) · Zbl 0538.05006
[4] Bhattacharyya, A, On a measure of divergence between two statistical populations defined by their probability distributions, Calcutta math. soc. bull., 35, 99-109, (1943) · Zbl 0063.00364
[5] Chernoff, H, A measure of asymptotic efficiency for tests of a hypothesis based on a sum of observations, Ann. math. stat., 23, 493-507, (1952) · Zbl 0048.11804
[6] Chung, J.K; Kannappan, Pl; Ng, C.T, A generalization of the cosine-sine functional equation on groups, Linear algebra appl., 66, 259-277, (1985) · Zbl 0564.39002
[7] Dhombres, J, Some aspects of functional equations, (1979), Chulalongkorn Univ. Press Bangkok · Zbl 0421.39005
[8] {\scP. Halland, P. L. Brockett, and A. Levine}, A characterization of divergence with application to questionnaire information, submitted for publication.
[9] Hellinger, E, Die orthogonalvarianten quadratischer formen von unendlich vielen variablelen, Dissertation, (1907), Gottingen · JFM 38.0153.01
[10] Jeffreys, H, An invariant form for the prior probability in estimation problems, (), 453-461 · Zbl 0063.03050
[11] Kailath, T, The divergence and bhattacharyya distance measures in signal selection, IEEE trans. comm. tech., COM-15, 52-60, (1967)
[12] Kannappan, Pl, On directed divergence and inaccuracy, Z. wahrsch. verw. gebiete, 25, 49-55, (1972) · Zbl 0248.94029
[13] Kannappan, Pl, Theory of functional equations, Matscience report 48, (1969), Madras · Zbl 0282.39005
[14] {\scPl. Kannappan and P. N. Rathie}, An axiomatic characterization of J-divergence, Submitted for publication. · Zbl 0678.62012
[15] Kullback, S, Information theory and statistics, (1978), Peter Smith Gloucester, MA · Zbl 0149.37901
[16] Ng, C.T, Representation for measures of information with the branching property, Inform. and control, 25, 45-56, (1974) · Zbl 0279.94018
[17] Rathie, P.N; Kannappan, Pl, A directed divergence function of type β, Inform. and control, 20, 38-45, (1972) · Zbl 0231.94015
[18] Sahoo, P, On some functional equation connected to sum form information measures on open domains, Utilitas math., 23, 161-175, (1983) · Zbl 0524.94008
[19] Sawyer, K.R, Testing separate families of hypotheses: an information criterion, J. roy. statist. soc. B, 45, 89-99, (1983) · Zbl 0515.62006
[20] Sawyer, K.R, A multiple divergence criterion for testing between separate hypotheses, Statist. probab. lett., 1, 26-30, (1982) · Zbl 0549.62022
[21] Sheng, L.T; Rathie, P.N, The J-divergence of order α, J. combin. inform. system sci., 6, 197-205, (1981) · Zbl 0497.94006
[22] Tou, J.T; Gonzales, R.C, Pattern recognition principle, (1974), Addison-Wesley Reading, MA
[23] Veglius, J; Janson, S; Johansson, F, Measures of similarity between distributions, Quality and quantity, 20, 437-441, (1986)
[24] Young, T.Y; Calvert, T.W, Classification, estimation and pattern recognition, (1974), Amer. Elsevier New York · Zbl 0185.47903
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.