Workshop FDA: Registration
View Submission - CRONOSFDA2018
A0177
Title: Functional insights into Google AdWords Authors:  Christoph Rust - WU Vienna University of Economics and Business and University of Regensburg (Germany) [presenting]
Dominik Liebl - University Bonn (Germany)
Stefan Rameseder - Regensburg (Germany)
Abstract: The functional linear regression model with points of impact is a recent augmentation of the classical functional linear model with many practically important applications. However, we demonstrate that the existing procedure for estimating the parameters of this regression model can be very inaccurate for practical sample sizes. A particularly problematic aspect is the tendency to omit relevant points of impact resulting in omitted variable biases. Therefore, we provide an adjusted estimation algorithm which is designed to compensate for this impractical small sample behavior. Our estimation algorithm is compared with the existing estimation procedure using extensive Monte Carlo simulations. Applicability of our estimation algorithm is demonstrated using data from Google AdWords, todays most important platform for online advertisements.