Investigation of Gender Differences in Large-Truck Crash Injury Severity in Missouri

Bernard Bracy, Jill M; Mondy, Christopher · 2018 · ROSA P / Iowa State University. Institute for Transportation

archive: archived pipeline: cataloged verified

Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)

Summary

This study investigates gender-specific differences in the factors influencing injury severity in large-truck crashes, motivated by the need to enhance driver training programs amid a national truck driver shortage. The authors theorize that the circumstances contributing to crash severity vary by gender, and identifying these differences could allow for more targeted safety education. The research focuses on Commercial Driver’s License (CDL) holders in Missouri, analyzing crash data from 2002 to 2012 obtained from the Missouri State Highway Patrol STARS database. The dataset includes 30,904 crashes where a Missouri-licensed CDL driver was determined to have contributed to the incident, categorized by severity into fatality, injury, or property damage only. The researchers employed Chi-squared Automatic Interaction Detection (CHAID) decision tree models to analyze the data, partitioning the dataset by gender to uncover complex patterns and predictor importance. The models used contributing circumstances—such as speeding, following distance, and physical impairment—as predictor variables for crash severity outcomes. The data were split into training (75%) and testing (25%) sets to validate model accuracy and prevent overfitting. The final models demonstrated high accuracy, with male driver models achieving approximately 80.6% accuracy on the testing set and female driver models achieving 79.4%. The study also expanded the analysis to include environmental factors, such as lighting, weather, and road conditions, to assess their impact on severity for each gender. The results reveal distinct predictors of crash severity for male and female drivers. For male CDL drivers, the most significant predictors were driving too fast for conditions, failing to yield, and physical impairment. The model identified significant interaction effects for males; for instance, driving too fast for conditions combined with driving on the wrong side of the road increased the probability of a fatal outcome to 8.1%. Conversely, for female CDL drivers, the primary predictors were following too closely, physical impairment, and improper passing. The model for female drivers did not identify significant interaction effects among variables, suggesting that contributing circumstances affect severity in isolation. Additionally, environmental factors were found to be statistically significant but marginal for male drivers, while they were not significant predictors for female drivers. The study concludes that truck driver training programs should be customized to address gender-specific behaviors. Training for male drivers should emphasize aggressive driving behaviors and the interaction of multiple risk factors, whereas training for female drivers should focus on maintaining proper following distances and avoiding driving while ill or fatigued. The authors note that the small sample size of female drivers is a limitation and recommend future research combine data from multiple states to improve statistical power and policy recommendations.

Key finding

Driving too fast for conditions and failing to yield are the top predictors of crash severity for male CDL drivers, whereas following too closely and improper passing are the top predictors for female CDL drivers.

Methodology

dataset

Sample size: 30904

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• sex gender
• demographic disparities
• pre crash contributing factors
• bus coach
• incidence prevalence
• causation analyses

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Empirical Findings: crash risk outcomes