In recent years, pedestrian justice has gained increasing attention. Particularly in Taipei City, Taiwan, where public transportation is highly accessible, ensuring pedestrian safety has become a key issue in urban planning. Previous studies have primarily relied on questionnaire surveys to evaluate walkability, while systematic integration of spatial analysis with empirical accident data remains relatively limited. This study takes Taipei City, Taiwan as a case study to explore the spatial relationship between walkability indicators and pedestrian traffic accidents.

A multi-step spatial analysis framework is employed in this study. First, Moran’s I is used to examine the global spatial autocorrelation of traffic accidents, followed by Local Moran’s I to identify potential high-risk clusters. Kernel density analysis is then applied to visualize the spatial concentration of accident hotspots. To further investigate the interaction between the built environment and accidents, the bivariate Local Indicators of Spatial Association (bivariate LISA) is utilized to capture the localized relationship between walkability indicators and accident locations. Finally, a Poisson regression model is applied to assess the statistical associations between explanatory variables (walkability features) and the frequency of pedestrian accidents.

By integrating multiple spatial analysis techniques, this study aims to provide a systematic framework for understanding how walkability influences pedestrian safety outcomes. The findings are expected to advance the methodological development of spatial analysis and offer practical insights for international urban safety planning