< Back to previous page

Project

Improving Kernel Change Point detection by pooling information across subjects and variables

Individuals can be conceived as complex dynamic systems, whose thoughts, feelings and behavior fluctuate across time. These fluctuations are governed by system features such as emotional differentiation, emotional variability and emotional inertia. Cross-sectional and prospective studies have shown evidence that these system features are related to psychopathology. These results raise the question whether mental health problems are preceded by changes in these features. In my dissertation, I showed  that Kernel Change Point detection (KCP) is a useful tool for answering this question as it allows to signal change points in the system features. In this PDM, we will further enhance the detection power of this method by addressing two major analytical challenges encountered in a typical ESM (experience sampling method) study: too few times points and highly correlated variables.

Date:1 Oct 2018 →  30 Sep 2019
Keywords:Kemel change point
Disciplines:Applied mathematics in specific fields, Statistics and numerical methods, Applied psychology, Biological and physiological psychology, General psychology, Other psychology and cognitive sciences