Results 1 
3 of
3
On Optimal Global Rates Of Convergence For Nonparametric Regression With Random Design
, 2000
"... this paper is to show that it is possible to achieve for ksmooth regression functions the wellknown optimal global rate of convergence n ..."
Abstract

Cited by 8 (4 self)
 Add to MetaCart
this paper is to show that it is possible to achieve for ksmooth regression functions the wellknown optimal global rate of convergence n
Universal Consistency of Local Polynomial Kernel Regression Estimates
, 2000
"... Regression function estimation from independent and identically distributed data is considered. The L 2 error with integration with respect to the design measure is used as an error criterion. It is shown that suitably dened local polynomial kernel estimates are weakly and strongly universally consi ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Regression function estimation from independent and identically distributed data is considered. The L 2 error with integration with respect to the design measure is used as an error criterion. It is shown that suitably dened local polynomial kernel estimates are weakly and strongly universally consistent, i.e., it is shown that the L 2 errors of these estimates converge to zero almost surely and in L 1 for all distributions.
Strong Consistency of Automatic Kernel Regression Estimates
, 2001
"... Regression function estimation from independent and identically distributed bounded data is considered. The L 2 error with integration with respect to the design measure is used as an error criterion. It is shown that the kernel regression estimate with an arbitrary random bandwidth is weakly and st ..."
Abstract
 Add to MetaCart
Regression function estimation from independent and identically distributed bounded data is considered. The L 2 error with integration with respect to the design measure is used as an error criterion. It is shown that the kernel regression estimate with an arbitrary random bandwidth is weakly and strongly consistent for all distributions whenever the random bandwidth is chosen from some deterministic interval whose upper and lower bounds satisfy the usual conditions used to prove consistency of the kernel estimate for deterministic bandwidths. Choosing discrete bandwidths by crossvalidation allows to weaken the conditions on the bandwidths.