On Estimation and Prediction in a Spatial Semi-Functional Linear Regression Model with Derivatives
摘要
Abstract
In this paper, we tackle estimation and prediction at non-vistedsites in a spatial semi-functional linear regression model withderivatives that combines a functional linear model with anonparametric regression one. The parametric part is estimated bya method of moments and the other one by a local linear estimator.We establish the convergence rate of the resulting estimators andpredictor. A simulation study and an application to ozonepollution prediction at non-visited sites are proposed toillustrate our results.