An Analysis of Spanish Accidents in Automobile Insurance: The Use of the Probit Model and the Theoretical Potential of Other Econometric Tools
Keywords:automobile insurance, claims, probit model, zero-inflated models, thinned models
Automobile insurance is one of the main pillars of the entire insurance industry in the developed economies. Knowing as much as possible about the factors related to the accidents is an essential issue for the insurance companies so that they may improve their levels of efficiency. Therefore, in this paper we focus on studying the most relevant variables that help explain the registration of claims in the automobile insurance sector. For this purpose, we fit a probit model specification using a database from a Spanish insurance company. Our research points out the significance of certain variables, such as the policyholders? driving experience, their region of residence as well as their levels of insurance coverage, towards the likelihood of registering an insurance claim. However, probit analysis represents only one of the multiple perspectives which we can consider to examine the question of accidents and their reporting. Very briefly, we also discuss the utility of zero-inflated count data models to study the number of accidents declared by policyholders. Finally, we point out the possibilities that thinned models could offer for this type of research.
Cameron A. C., Trivedi P. K. (1998), Regression Analysis of Count Data, Cambridge University Press, Cambrigde.
Chiappori P. A., Salanié B. (2000), Testing for Asymmetric Information in Insurance Markets, ?Journal of Political Economy?, Vol. 108, No. 1.
Cohen A. (2005), Asymmetric Information and Learning: Evidence from the Automobile Insurance Market, ?Review of Economics and Statistics?, Vol. 87, No. 2.
DGSFP - Dirección General de Seguros y Fondos de Pensiones (2010), Seguros y Fondos de Pensiones. Informe 2009, Ministerio de Economía y Hacienda, Madrid.
DGT - Dirección General de Tráfico (2004), Anuario Estadístico General 2003, Ministerio del Interior, Madrid.
Dionne G., Gouriéroux C., Vanasse C. (1999), Evidence of Adverse Selection in Automobile Insurance Markets, [in:] Dionne G., Laberge-Nadeau C. (eds.), Automobile Insurance: Road Safety, New Drivers, Risks, Insurance Fraud and Regulation, Kluwer Academic Publishers.
Gujarati, D.N. (2003), Basic Econometrics, 4th ed., McGraw-Hill.
Hausman J.A. (1978), Specification Tests in Econometrics, ?Econometrica?, Vol. 46, No. 6.
Lee A. H., Stevenson M. R., Wang K., Yau K. K. W. (2002), Modeling Young Driver Motor Vehicle Crashes: Data with Extra Zeros, ?Accident Analysis and Prevention?, Vol. 34, No. 4.
Melgar M. C., Ordaz, J. A., Guerrero, F. M. (2005), Diverses Alternatives pour Déterminer les Facteurs Significatifs de la Fréquence d?Accidents dans l?Assurance Automobile, ?Assurances et Gestion des Risques-Insurance and Risk Management?, Vol. 73, No. 1.
Melgar M. C., Ordaz J. A., Guerrero F. M. (2006), Une étude économétrique du nombre d?accidents dans le secteur de l?assurance automobile, ?Brussels Economic Review ? Cahiers Economiques de Bruxelles?, Vol. 49, No. 2.
Ordaz J.A., Melgar, M. C. (2010a), Covariate-Based Pricing of Automobile Insurance, ?Insurance Markets and Companies: Analyses and Actuarial Computations?, Vol. 1, No. 2.
Ordaz J.A., Melgar, M. C. (2010b), The Utility of Zero-Inflated Models in the Estimation of the Number of Accidents in the Automobile Insurance Industry, ?Equilibrium?, Vol. 2, No. 5.
Puelz R., Snow, A. (1994), Evidence on Adverse Selection: Equilibrium Signaling and Cross-Subsidization in the Insurance Market, ?Journal of Political Economy?, Vol. 102, No. 2.
Ronis D. L., Harrison K. A. (1988), Statistical Interactions in Studies of Physician Utilization, ?Medical Care?, Vol. 26, No. 4.
Shankar V., Milton J., Mannering F. (1997), Modeling Accident Frequencies as Zero-Altered Probability Processes: an Empirical Inquiry, ?Accident Analysis and Prevention?, Vol. 29, No. 6.