Speaker：Prof. Yi-Ju Chen (Department of Statistics, NCCU)
Topic：Geographically weighted regression models for nonnegative continuous response variables: An application to Taiwan dengue data
Speaker：Prof. Yi-Ju Chen (Department of Statistics, NCCU)
Date Time：Fri. Oct 18, 2024, 10:40-11:30
Place： 4F-427, Assembly Building I
Online Seminars- Google Meet
Abstract
Geographically weighted regression (GWR) is a popular tool used in many disciplines to explore spatial nonstationarity (or heterogeneity) with respect to data relationships in georeferenced data. However, GWR is typically limited to the analysis of continuous dependent variables that are assumed to follow a symmetric normal distribution. In many fields, nonnegative continuous data are frequently observed and may contain significant amounts of zeros followed by a right-skewed distribution of positive values. When modeling such type of response variables, GWR may not provide adequate insight into spatially varying regression relationships. This study aims to extend the GWR based on a compound Poisson distribution. Such an extension not only allows for the exploration of relationship heterogeneity, but also accommodates nonnegative continuous response variables. We provide a detailed model specification, discuss related modeling issues, and then evaluate the performance of the proposed method through simulations. Finally, we present an empirical case study using a dataset on dengue fever in Tainan, Taiwan, to demonstrate the practical applicability and utility of our approach.