CMStatistics 2017: Start Registration
View Submission - CMStatistics
B1012
Title: Boosting functional response models for location, scale and shape with an application to bacterial competition Authors:  Almond Stoecker - Humboldt University of Berlin (Germany) [presenting]
Sarah Brockhaus - Ludwig-Maximilians-University Munich (Germany)
Sophia Schaffer - LMU Munich (Germany)
Benedikt von Bronk - LMU Munich (Germany)
Madeleine Opitz - LMU Munich (Germany)
Sonja Greven - LMU Munich (Germany)
Abstract: Generalized Additive Models for Location, Scale, and Shape (GAMLSS) are extended to regression with functional responses. GAMLSS are a flexible model class allowing for modeling multiple distributional parameters at once. The model is fitted via gradient boosting, which provides inherent model selection. We apply the functional GAMLSS to analyze bacterial interaction in Escherichia coli and show how the consideration of variance structure fruitfully extends usual growth models.