|Authors:||Stein Fosser, Peter Christensen|
The partial relationship between automobile age and risk is studied by means of logistic regression as applied to a large insurance policy data set. Annual mileage and car owner's gender, age and county of residence are controlled for. Contrary to expectations, the analysis reveals a negative relationship between automobile age and risk. Older cars sustain fewer liability damage accidents, and also fewer injury accidents, than do new cars, other things being equal. It is suspected this is due to risk compensation.