ANALYSIS ON THE INFLUENCE FACTORS OF PASSENGER BY USING SMALL SAMPLE SIZE OF SUBWAY STATIONS

Abstract

This study is an extension of existing station-level ridership model for a small sample case. The aim is to explore and explain the factors influencing subway ridership. A small sample case with dozens of stations has a higher risk of both type I and type II errors in statistic when identifying the valid explanatory variables for ridership. To reduce this risk, a procedure using exploratory regression was proposed to identify the effective variables, and then the Mix Geographically Weighted Regression (MGWR) model is adopted to estimate the relevance of explanatory variables and subway ridership. This study uses the subway stations in Fukuoka, Japan as the study case. As the result, nine effective factors are selected from candidate explanatory variables for interpreting the variation of subway ridership.