Open Access
Translator Disclaimer
June 2011 Causal inference in transportation safety studies: Comparison of potential outcomes and causal diagrams
Vishesh Karwa, Aleksandra B. Slavković, Eric T. Donnell
Ann. Appl. Stat. 5(2B): 1428-1455 (June 2011). DOI: 10.1214/10-AOAS440

Abstract

The research questions that motivate transportation safety studies are causal in nature. Safety researchers typically use observational data to answer such questions, but often without appropriate causal inference methodology. The field of causal inference presents several modeling frameworks for probing empirical data to assess causal relations. This paper focuses on exploring the applicability of two such modeling frameworks—Causal Diagrams and Potential Outcomes—for a specific transportation safety problem. The causal effects of pavement marking retroreflectivity on safety of a road segment were estimated. More specifically, the results based on three different implementations of these frameworks on a real data set were compared: Inverse Propensity Score Weighting with regression adjustment and Propensity Score Matching with regression adjustment versus Causal Bayesian Network. The effect of increased pavement marking retroreflectivity was generally found to reduce the probability of target nighttime crashes. However, we found that the magnitude of the causal effects estimated are sensitive to the method used and to the assumptions being violated.

Citation

Download Citation

Vishesh Karwa. Aleksandra B. Slavković. Eric T. Donnell. "Causal inference in transportation safety studies: Comparison of potential outcomes and causal diagrams." Ann. Appl. Stat. 5 (2B) 1428 - 1455, June 2011. https://doi.org/10.1214/10-AOAS440

Information

Published: June 2011
First available in Project Euclid: 13 July 2011

zbMATH: 1223.62175
MathSciNet: MR2849781
Digital Object Identifier: 10.1214/10-AOAS440

Keywords: causal Bayesian networks , Causal inference , nighttime crash data , observational studies , potential outcomes , transportation safety

Rights: Copyright © 2011 Institute of Mathematical Statistics

JOURNAL ARTICLE
28 PAGES


SHARE
Vol.5 • No. 2B • June 2011
Back to Top