Abstract
In this paper, we introduce a new nonparametric estimation of the regression function when both the response and the explanatory variables are of the functional kind. First, we construct a local linear estimator of this regression operator, then we state its rate for the uniform almost complete convergence. This latter is expressed as a function of the small ball probability of the predictor and as a function of the entropy of the set on which the uniformity is obtained. (C) 2016 Academie des sciences. Publie par Elsevier Masson SAS.