Hostname: page-component-78c5997874-4rdpn Total loading time: 0 Render date: 2024-11-05T11:09:30.614Z Has data issue: false hasContentIssue false
  • English
  • Français

Assessing Individual Unexplained Variation in Non-Life Insurance

Published online by Cambridge University Press:  09 August 2013

Ola Hössjer ,
Bengt Eriksson ,
Kajsa Järnmalm  and
Esbjörn Ohlsson
Get access Rights & Permissions [Opens in a new window]

Abstract

We consider variation of observed claim frequencies in non-life insurance, modeled by Poisson regression with overdispersion. In order to quantify how much variation between insurance policies that is captured by the rating factors, one may use the coefficient of determination, R2, the estimated proportion of total variation explained by the model. We introduce a novel coefficient of individual determination (CID), which excludes noise variance and is defined as the estimated fraction of total individual variation explained by the model. We argue that CID is a more relevant measure of explained variation than R2 for data with Poisson variation. We also generalize previously used estimates and tests of overdispersion and introduce new coefficients of individual explained and unexplained variance.

Application to a Swedish three year motor TPL data set reveals that only 0.5% of the total variation and 11% of the total individual variation is explained by a model with seven rating factors, including interaction between sex and age. Even though the amount of overdispersion is small (4.4% of the noise variance) it is still highly significant. The coefficient of variation of explained and unexplained individual variation is 29% and 81% respectively.

Keywords

Claim frequency variationcoefficient of determinationcoefficient of individual determinationunexplained individual variationoverdispersionPoisson regressionrating factors
Type
Research Article
Information
ASTIN Bulletin: The Journal of the IAA , Volume 39 , Issue 1 , May 2009 , pp. 249 - 273
Copyright
Copyright © International Actuarial Association 2009

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Beard, R.E., Pentikainen, T. and Pesonen, E. (1984) Risk Theory, The Stochastic Basis of Insurance (3rd edition). Chapman and Hall.Google Scholar
Breslow, N.E. (1984) Extra-Poisson variation in log-linear models. Appl. Statist. 33(1), 38–44.Google Scholar
Brockman, M.J. and Wright, T.S. (1992) Statistical motor rating: Making effective use of your data. Journal of the Institute of Actuaries 119(111), 457–543.Google Scholar
Bühlmann, H. and Gisler, A. (2005) A Course in Credibility Theory and its Applications. Springer Universitext.Google Scholar
Cox, D.R. and Snell, E.J. (1989) The analysis of binary data, 2nd ed., Chapman and Hall, London.Google Scholar
Fisher, R.A. (1950) The significance of deviations from expectation in a Poisson series. Biometrics 6, 17–24.Google Scholar
Haight, F.A. (2001) Accident proneness: The history of an idea. Institute of Transportation Studies, University of California, Irvine, USA.Google Scholar
Hinde, J. (1982) Compound Poisson regression models. In GLIM 82: Proceedings of the International Conference in Generalized Linear Models (Gilchrist, R., ed.), pp. 199–121, Springer, Berlin.Google Scholar
Hössjer, O. (2008) On the coefficient of determination for mixed regression models. Journal of Statistical Planning and Inference 138, 3022–3038.Google Scholar
Johnson, P.D. and Hey, G.B. (1971) Statistical studies in motor insurance. Journal of the Institute of Actuaries 97, 199.Google Scholar
Jung, J. (1968) On automobile insurance ratemaking. ASTIN Bulletin 5, 41.Google Scholar
Järnmalm, K. (2006) Measures of the remaining systematic variance between individuals when divided into individual premium groups in non-life insurance. Master Thesis, Mathematical Statistics, Stockholm University, Report 2006:15. (In Swedish.)Google Scholar
Lawless, J.F. (1987) Negative binomial and mixed Poisson regression. Canadian J. Statist. 15(3), 209–225.Google Scholar
Lemaire, J. (1995) Bonus-Malus Systems in Automobile Insurance. Springer.Google Scholar
Maddala, G.S. (1983) Limited-Dependent and Qualitative Variables in Econometrics. Cambridge University Press.Google Scholar
Magee, L. (1990) R 2 measures based on Wald and likelihood ratio joint significance tests. Am. Statistician 44, 250–253.Google Scholar
McCullagh, P. and Nelder, J.A. (1989) Generalized Linear Models, second edition, Chapman and Hall.Google Scholar
Nagelkerke, N.J.D. (1991) A note on a general definition of the coefficient of determination. Biometrika 78(3), 691–692.Google Scholar
Ohlsson, E. (2008) Combining generalized linear models and credibility models in practice. Scandinavian Actuarial Journal 2008(4), 301–314.Google Scholar
Ohlsson, E. and Johansson, B. (2006) Exact credibility and Tweedie models. ASTIN Bulletin 36(1), 121–133.Google Scholar
Pearson, K. (1900) On a criterion that a given system of deviations from the probable in case of a correlated system of variables in such that it can be reasonably supposed to have arisen from a random sampling. Phil. Mag. 50(5), 157–75.Google Scholar
Pocock, S.J., Cook, D.G. and Beresford, S.A.A. (1981) Regression of area mortality rates on explanatory variables: what weighting is appropriate? Appl. Statist. 30, 286–295.Google Scholar
Rao, C.R. and Chakravarti, I.M. (1956) Some small sample tests for significance for a Poisson distribution. Biometrics 12, 264–282.Google Scholar
Venezian, E.C. (1981) Good drivers and bad drivers – a Markov model of accident proneness. Proceedings of the Casualty Actuarial Society, LXVII, 65–85.Google Scholar
Venezian, E.D. (1990) The distribution of automobile accidents – are relativities stable over time? Proceedings of the Casualty Actuarial Society, LXXVII, 309–336.Google Scholar
White, H. (1982) Maximum likelihood under misspecified models. Econometrica 50, 1–25.Google Scholar