A0812
Title: Generalized partially functional linear model based on multi-source data
Authors: Xiaochen Zhang - Beijing Normal University (China) [presenting]
Abstract: Multi-source data may be presented in different forms (such as scalar data, functional data, network data, etc.). The integration of multi-source data analysis is of significant importance, and the aim is to propose a generalized partially functional linear model for integrating functional data with other forms of data (such as network structures, scalar data, etc.) from different source domains. To improve the estimation and prediction, the network cohesion is enforced using the Laplace quadratic penalty function. Simulation results and real data application demonstrate the satisfactory performance of the proposed methods.
