Accelerated convergence for nonparametric regression with coarsened predictors

We consider nonparametric estimation of a regression function for a situation where precisely measured predictors are used to estimate the regression curve for coarsened, that is, less precise or contaminated predictors. Specifically, while one has available a sample of independent and identically distributed data, representing observations with precisely measured predictors, where , instead of the smooth regression function , the target of interest is another smooth regression function that pertains to predictors that are noisy versions of the . Our target is then the regression function , where is a contaminated version of , that is, . It is assumed that either the density of the errors is known, or replicated data are available resembling, but not necessarily the same as, the variables . In either case, and under suitable conditions, we obtain -rates of convergence of the proposed estimator and its derivatives, and establish a functional limit theorem. Weak convergence to a Gaussian limit process implies pointwise and uniform confidence intervals and -consistent estimators of extrema and zeros of . It is shown that these results are preserved under more general models in which is determined by an explanatory variable. Finite sample performance is investigated in simulations and illustrated by a real data example.
View on arXiv