Titlebook: Nonparametric Functional Estimation and Related Topics; George Roussas Book 1991 Springer Science+Business Media Dordrecht 1991 Estimator.

laceration

On the Nonparametric Estimation of the Entropy Functionalider the problem of estimating H(f) nonparametrically, based on a random sample X.,…,X. from the underlying density. Several methods to estimate H(f) have been put forward in the literature. Here, a new class of entropy estimators is considered. The common feature of these estimators is that they ar

平淡而无味

Analysis of Samples of Curvessh to exploit the sample information. As a first goal, we want to estimate a valid average curve which reflects the individual-dynamic and intensity. To this end, we try to align individual curves such that similar events or structures take place at identical times: This can be achieved via individu

火光在摇曳

Bootstrap Methods in Nonparametric Regressionar construction. The bootstrap provides a simple-to-implement alternative to procedures based on asymptotic arguments. In this paper we give an overview over the various bootstrap techniques that have been used and proposed in nonparametric regression. The bootstrap has to be adapted to the models a

焦虑

On the Influence Function of Maximum Penalized Likelihood Density Estimators.. It can explain some of the known behaviour of these estimates, e.g., their “bump-hunting” abilities. A study of the influence function suggests a larger class of estimators, which contains as special cases, both the kernel estimates and known MPLE’s. This is a two-parameter (p, h) class, where h i

Living-Will

结束

MUT

Nonparametric Estimation of Elliptically Contoured Densitiese analyze the large sample behavior of a kernel-type estimator of f, when both the parametric component (μ.) as well as the nonparametric transfer function k are unknown. It turns out that the rate of convergence is independent of d.

terazosin

Uniform Deconvolution: Nonparametric Maximum Likelihood and Inverse Estimationion ., we want to estimate . In this problem a maximum likelihood estimator of . can be derived, provided an extra support condition on . is satisfied. The problem can also be viewed as an inverse estimation problem. Since the transformation which maps the unknown distribution function . on the dist

不利

Explicate