In this paper the Kagan divergence measure is extended in order to establish a measure of the information that a random sample gives about a Dirichlet process as a whole. After studying some of its properties, the expression obtained in sampling from the step n to the step n+1 is given, and its Bayesian properties are studied. We finish proving the good behaviour of a stopping rule defined on the basis of the information obtained in sampling when passing from a step to the following.
@article{urn:eudml:doc:40420,
title = {La medida de divergencia de Kagan en el muestreo secuencial con procesos de Dirichlet.},
journal = {Trabajos de Estad\'\i stica},
volume = {1},
year = {1986},
pages = {88-96},
zbl = {0654.62006},
language = {es},
url = {http://dml.mathdoc.fr/item/urn:eudml:doc:40420}
}
Morales González, Domingo. La medida de divergencia de Kagan en el muestreo secuencial con procesos de Dirichlet.. Trabajos de Estadística, Tome 1 (1986) pp. 88-96. http://gdmltest.u-ga.fr/item/urn:eudml:doc:40420/