Page 1

Displaying 1 – 2 of 2

Showing per page

Information inequalities for the minimax risk of sequential estimators (with applications)

Lesław Gajek, B. Mizera-Florczak (1998)

Applicationes Mathematicae

Information inequalities for the minimax risk of sequential estimators are derived in the case where the loss is measured by the squared error of estimation plus a linear functional of the number of observations. The results are applied to construct minimax sequential estimators of: the failure rate in an exponential model with censored data, the expected proportion of uncensored observations in the proportional hazards model, the odds ratio in a binomial distribution and the expectation of exponential...

Invariance and R-ε criterion.

Julián de la Horra (1986)

Trabajos de Estadística

The R-ε criterion is considered as a generalization of the minimax criterion, in a decision problem with Θ = {θ1, ..., θn}, and its relation with the invariance is studied. If a decision problem is invariant under a finite group G, it is known, from the minimax point of view that, for any rule δ, there exists an invariant rule δ' which is either preferred or equivalent to δ. The question raised in this paper is: given that the minimax ordering is a particular case of R-ε ordering, is it possible...

Currently displaying 1 – 2 of 2

Page 1