01153237

Component

https://doi.org/10.3141/2148-07

http://scholar.google.com...kula&publication_year=2010

The evaluation of crash severities and the estimation of crash costs are key elements in evidence-based traffic safety improvement programs. Police records include information on injury severity estimated at the scene either by a police officer or by a medical emergency unit. At a hospital, the accident injuries are examined and documented more thoroughly and thus provide a better basis for cost estimation. Using hospital injury data for priority ranking of transportation projects and in other decision-making processes requires linking medical and crash records. Unfortunately, only a modest portion of crash records can be linked to corresponding medical records, even if a person is hospitalized, because missing data hamper the linking process. This study proposes a new method to overcome these difficulties and to estimate the expected level of injury of individuals included in all police-reported crashes. This method is accomplished by developing statistical models based on the linked medical and crash records and by applying these models to the entire crash data set. A fundamental problem to overcome was the selectivity bias present in the linked data and caused by the injury criteria for directing individuals to hospitals. The concept and the development of the proposed method are presented. The method is illustrated with its components developed with Indiana linked data and applied to Indiana crash data for 2005 to 2006.

01164464

10-2281

English

pp 59-68

2010

Transportation Research Record: Journal of the Transportation Research Board

9780309142793

Print

Figures (3) ; References (44) ; Tables (4)

Costs; Crash data; Crash injuries; Crash records; Crash severity; Highway safety; Hospitals; Injury severity; Medical records; Police reports; Traffic crashes

Abbreviated Injury Scale

Accident costs; Linked data

Indiana

Data and Information Technology; Highways; Safety and Human Factors; I81: Accident Statistics; I84: Personal Injuries

TRIS, TRB, ATRI

Jan 25 2010 11:03AM

• County-Level Crash Risk Analysis in Florida: Bayesian Spatial Modeling
• Crash Generation Models: Forecasting Crashes in Urban Areas
• Evaluating Trauma Management Performance in Europe: A Multiple-Layer Data Envelopment Analysis Model
• Exploratory Study of Mechanisms by Which Exposure Influences Accident Occurrence
• Fatality Risk of Intersection Crashes on Rural Undivided Highways in Alberta, Canada
• Full Bayes Approach to Before-and-After Safety Evaluation with Matched Comparisons: Case Study of Stop-Sign In-Fill Program
• Impact of Rumble Strips on Collision Reduction on Highways in British Columbia, Canada: Comprehensive Before-and-After Safety Study
• Implementation Road Map for In-Vehicle Safety Systems in China
• Logistic Models in Crash Severity Classification Based on Road Characteristics
• Ordinal Discrete Choice Analyses of Wisconsin Cross-Median Crash Severities
• Property Damage Crash Equivalency Factors to Solve Crash Frequency–Severity Dilemma: Case Study on South Korean Rural Roads
• Rethinking Electronic Crash Data Collection Transmission Model: Conceptual Framework for Centralized Web-Based Crash Data Collection System
• Revisiting Variability of Dispersion Parameter of Safety Performance for Two-Lane Rural Roads