CMStatistics 2017: Start Registration
View Submission - CMStatistics
Title: Generalized functional linear models with points of impact Authors:  Dominik Poss - University of Bonn (Germany) [presenting]
Dominik Liebl - University Bonn (Germany)
Abstract: A generalized functional linear regression model with points of impact is assumed. In the classical generalized functional linear regression model, scalar responses $Y_1,\dots,Y_n$ are connected to the inner product of functional predictors $X_1,\dots, X_n$ and an unknown coefficient function via a smooth link function. Additionally, an unknown number of unknown specific locations (``points of impact'') at which the functional predictor will have a further effect on the response are allowed. The focus is on the estimation of these points of impact. Some theoretical results are given and the estimation procedure is illustrated in the case of a (functional) logistic regression framework with points of impact where the depend variable $Y_i$ is binary.