MODELING THE SPATIO-TEMPORAL RELATIONSHIPS FOR THE DISTRIBUTION OF POPULATION WITH GEOGRAPHICALLY AND TEMPORALLY WEIGHTED REGRESSION

Abstract

 This paper applies a spatio-temporal model to assess the variability of local parameters associated with the urban population change over time. With the Person Trip survey dataset and the detailed digital map of land use, Geographically and Temporally Weighted Regression (GTWR) is used to analyze the relationship between distributions of occupants inside residential buildings and commercial buildings in Tokyo Metropolitan Area (TMA). The outcome of the models has shown that GTWR has higher explanatory power (R²=95%) compared to global regression model (R²=0.5%) and Geographically Weighted Regression (R²=91%). Furthermore, there is a significant pattern of spatio-temporal characteristics for distribution of populations at the inner city, its neighborhoods and suburbs of Tokyo.