An Empirical Bayes Approach to Quantifying the Impact of Transportation Network Companies (TNCs) on VMT

Assessing the impacts of new and disruptive technologies on automobile usage and the modal split is emerging as a key issue for transportation planners and policymakers. The proposed research will offer a new approach to quantifying the impact of TNCs (Transportation network companies such as Uber and Lyft) on VMT (Vehicle‐Miles Traveled). The approach is based on a simple idea from counterfactual theory, which is to compare VMT estimates after the TNCs introduction to a region to what the VMT would have been without the TNCs. The later of the two is a counterfactual, and therefore more difficult to estimate. The proposed research will develop and demonstrate the Empirical Bayes (EB) measurement model for estimating counterfactual VMT estimate.The EB method is in fact widely used and accepted for traffic safety assessment. The approach proposed for estimating VMT changes is analogous to the quasi‐experimental EB procedure for estimating crash reduction if a particular traffic safety treatment is applied on a roadway location. In this research, the research team reinterprets the traffic safety treatment as being akin to the introduction of TNCs and the estimation of crash reduction as analogous to the resulting change in VMT. This research will develop an EB measurement model for the VMT in San Luis Obispo region as a proof‐of‐concept. Counterfactual VMT estimate will be obtained by combining VMT estimates from the cross‐sectional models (estimated using data from other regions) and VMT estimates based on longitudinal data from the San Luis Obispo region. The team expects the approach to be useful in estimating effects of CAV (Connected and Automated Vehicles) introduction on VMT as well in the future.