Abstract
The presence of outliers, in general, affects the performance of the conventional statistical methods which require the homogeneity of observations. In this study, we consider variable selection problem in a functional regression model when a functional dataset contains outliers. We propose a functional adaptive group LASSO variable selection method based on the weighted least absolute deviation which takes into account the effect of outliers in both x and y directions for a functional regression model with a scalar response and multiple functional predictors. Further, we demonstrate, through simulated and real datasets, that the proposed methods perform well.