Factors affecting public transportation usage rate: Geographically weighted regression. (August 2015)

• Record Type: Journal Article
• Authors: Chiou, Yu-Chiun; Jou, Rong-Chang; Yang, Cheng-Han
• Is Part Of: Transportation research. Volume 78(2015)
• Page Start: 161
• Page End: 177
• Publication Date: 2015-08
• Subjects: Public transportation usage rate -- Tobit regression -- Geographically weighted regression -- Spatial autocorrelation; Transportation -- Research -- Periodicals; 388.011
• DOI: 10.1016/j.tra.2015.05.016
• Languages: English
• ISSNs: 0965-8564

Abstract

Highlights: Global and local models are used to identify key factors of public transportation usage rates. Tobit regression model (global) and GWR model (local) are compared. GWR model performs better because of its capability in accommodating spatial correlations. Seven variables are significantly tested, and most have parameters that differ across regions. Strategies are proposed that improve public transportation usage accordingly. Abstract: As the number of private vehicles grows worldwide, so does air pollution and traffic congestion, which typically constrain economic development. To achieve transportation sustainability and continued economic development, the dependency on private vehicles must be decreased by increasing public transportation usage. However, without knowing the key factors that affect public transportation usage, developing strategies that effectively improve public transportation usage is impossible. Therefore, this study respectively applies global and local regression models to identify the key factors of usage rates for 348 regions (township or districts) in Taiwan. The global regression model, the Tobit regression model (TRM), is used to estimate one set of parameters that are associated with explanatory variables and explain regional differences in usage rates, while the local regression model, geographically weighted regression (GWR), estimates parameters differently depending on spatial correlations among neighbouring regions. By referencing related studies, 32 potential explanatory variables in four categories, social-economic, land use, public transportation, and private transportation, are chosen. Model performance is compared in terms of mean absolute percentage error (MAPE) and spatial autocorrelation coefficient (Moran' I ). Estimation results show that the GWR model has better prediction accuracy and better accommodation of spatial autocorrelation. Seven variables are significantly tested, and most have parameters that differ across regions in Taiwan. Based on these findings, strategies are proposed that improve public transportation usage.