Hostname: page-component-586b7cd67f-t7fkt Total loading time: 0 Render date: 2024-11-26T00:11:50.276Z Has data issue: false hasContentIssue false

Using Multi-Dimensional Credibility to Estimate Class Frequency Vectors in Workers Compensation

Published online by Cambridge University Press:  17 April 2015

Jose Couret
Affiliation:
Guy Carpenter, LLC, One Madison Avenue, New York, NY 10010, E-Mail: [email protected]
Gary Venter
Affiliation:
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

The US workers compensation system is different from those in many countries, but it is reinsured in the world-wide market and so has international impact. From its origin in the early 20th century it has been a laboratory for actuarial credibility techniques. In recent years deductibles have been increasing, so that fairly high excess coverage is now commonplace. This puts growing emphasis on estimation of the percentage of loss that is excess of high deductibles. A key element of the excess percentage is the frequency of loss by injury type. Fatalities and permanent disabilities cost more than other injury types, so when they have high relative frequency, more of the claims cost arises from large losses. The vector of claim frequency by injury type can be estimated by class of business using multi-dimensional credibility techniques. Historically the fraction of costs excess of various retentions has been calculated for large groups of classes (hazard groups) and not individual classes. We show, by testing a hold-out sample, that credibility estimation by class does produce additional information in comparison to a widely-used seven-hazard-group system.

Type
Articles
Copyright
Copyright © ASTIN Bulletin 2008

References

Black, F., Jensen, M. and Scholes, M. (1972) “The Capital Asset Pricing Model: Some Empirical Tests.” In Studies in the Theory of Capital Markets, ed. Jensen, Michael C. New York: Praeger.Google Scholar
Bodie, Z., Kane, A. and Marcus, A. (1999), Investments, 4th Edition, Irwin/McGraw-Hill, (pages 376378).Google Scholar
Dean, C. (2005) “Topics in Credibility Theory”, Education and Examination Committee of the Society of Actuaries, Construction and Evaluation of Actuarial Models Study Note.Google Scholar
Dorweiler, P. (1934) “A Survey of Risk Credibility in Experience Rating, Presidential Address at Twentieth Anniversary”, Proceedings of the Casualty Actuarial Society XXI(1).Google Scholar
Gillam, W. (1992) “Parametrizing the Workers Compensation Experience Rating Plan”, Proceedings of the Casualty Actuarial Society, LXXIX, 2156.Google Scholar
Hachemeister, C. (1975) “Credibility for Regression Models with Application to Trend”. In: Kahn, P. (Ed.), Credibility, Theory and Applications, Academic Press, New York.Google Scholar
Harwayne, F. (1966) “Insurance Cost of Automobile Basic Protection Plan in Relation to Automobile Bodily Injury Costs”, Proceedings of the Casualty Actuarial Society, LIII, 122158.Google Scholar
Venter, G. (1985) “Structured Credibility in Applications – Hierarchical, Multidimensional, and Multivariate Models”, Actuarial Research Clearing House, Vol. 2.Google Scholar