Regresión funcional mediante bases obtenidas por descomposición espectral del operador covarianza

Abstract

In this paper, we study a functional linear regression model in which explanatory variables are sampling points of a continuous-time process namely random function observed on a  compact subset of  , and Y is scalar response variable. We propose two estimators of regression: by means of a functional PCA method and by functional PLS method. Our aim is to compare coefficients of determination (R2) obtained by methods mentioned above.