Titlebook: Contributions to a General Asymptotic Statistical Theory; J. Pfanzagl Book 1982 Springer-Verlag, New York Inc. 1982 Asymptotische Wirksamk

占卜者

Differentiable Functionals,Let κ: β → IR be a functional. For asymptotic theory, the . . of this functional are essential, i.e., its behavior in contiguous neighborhoods. These local properties determine how good optimal tests and estimators can be asymptotically. The mathematical construct suitable for this purpose is the gradient.

intricacy

Genome

Distance Functions for Probability Measures,Let μ |. be a σ-finite measure and P, Q, P. , P. p-measures with μ- densities p, q, p., p..

施加

EXULT

Existence of Asymptotically Efficient Estimators for Probability Measures,For .∈x., let P. (., ·) denote a p-measure. Our problem is to evaluate the performance of P as an estimator for a p-measure known to belong to β. Throughout the following we assume that the estimator is strict, i.e. that P. (., ·) ∈β for every . ∈ x.. The basic problem is to define as. efficiency.

Processes

Inference for Parametric Families,Let β be a family of p-measures, and κ: β → IR a differentiable functional. Let κ(·,β the canonical gradient of κ at P.

機(jī)構(gòu)

harangue

Inference for Measures on Product Spaces,For i ∈ {1,. . .,m} let (x., .) be measurable spaces. In the following, sums Σ and products ×,Π over i always run from 1 to m. Let β be a family of p-measures on ×., and κ: β → IR a functional. Our problem is to estimate κ(P) under various conditions on β.

aesthetic

確定的事