Related Experiment Video
Updated: Aug 2, 2025

A Test Bed to Examine Helmet Fit and Retention and Biomechanical Measures of Head and Neck Injury in Simulated Impact
Published on: September 21, 2017
IIHS small overlap frontal crash test ratings and real-world driver death risk
Eric R Teoh1, Samuel S Monfort1
1Research Department, Insurance Institute for Highway Safety, Arlington, Virginia.
Objective:
To evaluate how ratings for the Insurance Institute for Highway Safety (IIHS) driver-side small-overlap frontal crash test predict real-world driver death risk in frontal impacts.
Methods:
IIHS released the driver-side small-overlap frontal crash test in 2012, after manufacturers had improved vehicle designs to make good ratings in the IIHS moderate overlap frontal crash test virtually ubiquitous. In the small overlap test, the vehicle impacts a rigid barrier at 40 mph (64 km/h) with 25% of the vehicle's width overlapping the barrier. As in other IIHS tests, vehicles are rated as good, acceptable, marginal, or poor. Drivers' risk of dying in a frontal crash was estimated by dividing driver deaths by driver involvements in police-reported crashes and modeling with logistic regression to estimate the effect of crash test rating, while controlling for driver age and sex, vehicle type and curb weight, and number of vehicles in the crash.
Results:
Drivers of good-rated vehicles were 12% less likely to die in frontal impacts than drivers of poor-rated vehicles. This estimate was 11% for acceptable-rated vehicles and 5% (not statistically significant) for marginal-rated vehicles, compared with vehicles rated poor.
Conclusions:
The current study demonstrates that the IIHS driver-side small-overlap crash test rating encourages vehicle designs that reduce drivers' real-world risk of dying in frontal crashes.
Related Concept Videos
Hypothesis Test for Test of Independence
H0: The two variables (factors)...
Relative Risk
Hazard Ratio
For example, in a clinical trial...
Introduction to Test of Independence
The test statistic for a test of independence is similar to that of a goodness-of-fit test:
Finding Critical Values for Chi-Square
Determination of Expected Frequency

