Measuring the Cost Effectiveness of Multimode Bus Transit in the Presence of Accident Risks

Abstract

This study employs the directional graph distance function and the multiactivity data envelopment analysis (DEA) approach, which incorporates both desirable and undesirable outputs, in order to provide a more complete representation of the multimode bus production technology from which environmentally and risk-sensitive cost effectiveness measures can be generated. We treat accident cost as the risky output in the sense that we wish to increase desirable outputs and decrease risky output and inputs. The approach is applied to the problem of measuring the cost effectiveness of 24 bus companies in Taiwan. An empirical illustration suggests that the overall cost effectiveness rankings turn out to be very sensitive to whether or not the graph multiactivity DEA approach is adopted. This implies that the conventional DEA cost effectiveness measure may be seriously misleading if it ignores the cost effectiveness of organizations that carry out various activities whilst sharing common resources.