Minimum divergence estimators based on grouped data

Journal Article

Menéndez M. L., Morales D., Pardo L., Vajda Igor

serial: Annals of the Institute of Statistical Mathematics vol.53, 2 (2001), p. 277-288

research: AV0Z1075907

project(s): GA102/99/1137, GA ČR

keywords: minimum divergence estimators, random quantization, asymptotic normality

abstract (eng):

It is shown that an optimal grouping of data (quantification) leads to a negligible inefficiency in continuous parametric models. Robust estimators achieving the negligible inefficiency are introduced and their asymptotic theory is established.

Cosati: 12B

RIV: BB