Contributed Poster Presentations: Transportation Statistics Interest Group

Transportation data on real world events can be quite messy. Models trained on these data often exhibit misclassification patterns impacting inferences made. This is a particular issue in safety research where the models are used for crash prediction. This study presents a framework for identifying and analyzing systematic prediction error. Data related to pedestrian-vehicle crashes at intersections in Seattle, Washington is used to distinguish between locations prone to temporally systematic and spatially random prediction biases. The framework identified significant geographic heterogeneity in model performance and temporally consistent error patterns. A manual labeling protocol using Google Street View showed environmental features (e.g., sight-line obstructions, infrastructure conditions) originally absent from the training data. This analysis reduced manual review requirements by identifying spatial and temporal components contributing to systematic biases observed in naturalistic data. The framework can be used in future crash prediction models to establish protocols for systematic pattern detection and new feature extraction. 

In longitudinal data, unobserved confounders often vary by unit and time period. A common approach for adjusting for these confounders is to use instrumental variables in combination with two-way fixed effects. However, this approach requires that any unobserved confounders
correlated with the instrument vary solely by unit or time period, with no interactions between the two. In this paper, we relax this assumption by proposing a novel method in which instrumental variable regression is estimated with interactive fixed effects. Our method leverages nuclear norm penalization to adjust for confounders that vary across both unit and time period, assuming the variation is low-rank. We first demonstrate that under this assumption, the proposed estimator yields a consistent estimator of the average treatment effect. We then apply our method to investigate the relationship of traffic ticket issuance and car accident rates. The results of our analysis indicate that traffic tickets issued by police officers in New York City effectively reduce traffic collisions. Finally, we validate the efficacy and robustness of our approach by comparing it with competing methods. 

The Covid-19 pandemic has brought about shifts in activity patterns and travel behaviours, resulting in fluctuations in mass transit ridership. There were significant declines in ridership across all systems during lockdowns. However, after the lifting of travel restrictions, some metro systems have implemented fare reductions to stimulate demand in response to sluggish ridership growth. This study aims to conduct a causal analysis of the impact of pricing policies on ridership recovery in urban metro systems during the post-pandemic period. Regression discontinuity design and synthetic control methods are employed to estimate the average treatment effect of fare reductions, which serves as the basis for deriving price-demand elasticities. To ensure the robustness of our findings, Placebo tests are conducted to validate the results.