Displaying similar documents to “On a class of perimeter-type distances of probability distributions”

Blended φ -divergences with examples

Václav Kůs (2003)

Kybernetika

Similarity:

Several new examples of divergences emerged in the recent literature called blended divergences. Mostly these examples are constructed by the modification or parametrization of the old well-known phi-divergences. Newly introduced parameter is often called blending parameter. In this paper we present compact theory of blended divergences which provides us with a generally applicable method for finding new classes of divergences containing any two divergences D 0 and D 1 given in advance....

The Bhattacharyya metric as an absolute similarity measure for frequency coded data

Frank J. Aherne, Neil A. Thacker, Peter I Rockett (1998)

Kybernetika

Similarity:

This paper highlights advantageous properties of the Bhattacharyya metric over the chi-squared statistic for comparing frequency distributed data. The original interpretation of the Bhattacharyya metric as a geometric similarity measure is reviewed and it is pointed out that this derivation is independent of the use of the Bhattacharyya measure as an upper bound on the probability of misclassification in a two-class problem. The affinity between the Bhattacharyya and Matusita measures...

Goodness-of-fit tests based on K φ -divergence

Teresa Pérez, Julio A. Pardo (2003)

Kybernetika

Similarity:

In this paper a new family of statistics based on K φ -divergence for testing goodness-of-fit under composite null hypotheses are considered. The asymptotic distribution of this test is obtained when the unspecified parameters are estimated by maximum likelihood as well as minimum K φ -divergence.