Performance evaluation for demand responsive transport services: A two-stage bootstrap-DEA and ordinary least square approach

Demand responsive transport (DRT) services have often been introduced to provide flexible public transport services, especially for areas with dispersed demand. However, objectively evaluating the performance of DRT services is challenging. This study uses a two-stage bootstrapped DEA and Ordinary Least Square (OLS) approach to measure performance using the Taiwanese DRT services as the empirical setting. In the first stage, bias-corrected Data Envelopment Analysis (DEA) efficiency scores are calculated by employing the smoothed homogenous bootstrapped procedure (Simar & Wilson, 2000). In the second stage, a OLS regression model is used to explore the impact from external factors with bias-corrected DEA efficiency scores as the dependent variable. Model results confirm that more than half of DRT services have increasing return to scale. The model results also show heavy rail services bring significant negative impact to the DRT service performance. This finding implies the main users of DRT services are local residents with fewer intercity travellers who typically would use heavy rail for access. The model results can lead to an improvement strategy for DRT services, for example, having a strategy to attract tourists to use DRT services to access tourist attraction sites would be one way to increase demand which would have the added advantage of improving sustainability. This study evaluates how this might improve public transport network accessibility and concludes with recommendations of a way forward to provide more sustainable DRT services.