We consider a problem of estimation of parametric components in a partial linear model. Suppose that a finite set E of linear estimators is given. Our goal is to mimic the estimator in E that has the smallest risk. Using a second order expansion of the risk of linear estimators we propose a...

The problem of estimation of the finite dimensional parameter in a partial linear model is considered. We derive upper and lower bounds for the second minimax order risk and show that the second order minimax estimator is a penalized maximum likelihood estimator. It is well known that the...

We consider a problem of estimation of parametric component in a partial linear model. Suppose that a finite set E of linear estimators is given. Our goal is to mimic the estimator in E that has the smallest risk. Using a second order expansion of the risk of linear estimators we propose a...

Let (X1, Y1), . . ., (Xn, Yn) be i.i.d. rvs and let l(x) be the unknownp-quantile regression curve of Y on X. A quantile-smootherln(x) is a localised, nonlinear estimator of l(x). The strong uniformconsistency rate is established under general conditions. In many applicationsit is necessary to...