Advertisement

Predicting Future Claims Among High Risk Policyholders Using Random Effects

  • Clara-Cecilie GüntherEmail author
  • Ingunn Fride Tvete
  • Kjersti Aas
  • Jørgen Andreas Hagen
  • Lars Kvifte
  • Ørnulf Borgan
Chapter
Part of the EAA Series book series (EAAS)

Abstract

Insurance claims are often modelled by a standard Poisson model with fixed effects. With such a model, no individual adjustments are made to account for unobserved heterogeneity between policyholders. A Poisson model with random effects makes it possible to detect policyholders with a high or low individual risk. The premium can then be adjusted accordingly. Others have applied such models without much focus on the model’s prediction performance. As the usefulness of an insurance claims model typically is measured by its ability to predict future claims, we have chosen to focus on this aspect of the model. We model insurance claims with a Poisson random effects model and compare its performance with the standard Poisson fixed effects model. We show that the random effects model both fits the data better and gives better predictions for future claims for high risk policy holders than the standard model.

Notes

Acknowledgments

This work was financed by the centre Statistics for innovation (sfi\(^2\)). The authors thank Gjensidige for kindly providing the data and Lars Holden for valuable suggestions.

References

  1. 1.
    Agresti, A.: Categorical Data Analysis, 2nd edn. Wiley-Interscience, Hoboken (2000)Google Scholar
  2. 2.
    Antonio, K., Valdez, E.A.: Statistical concepts of a priori and a posteriori risk classification in insurance. AStA Adv. Stat. Anal. 96, 187–224 (2012)Google Scholar
  3. 3.
    Bates, D., Maechler, M., Bolker, B.: lme4: Linear mixed-effects models using S4 classes. R package version 0.999375-42 (2011)Google Scholar
  4. 4.
    Boucher, J.-P., Denuit, M.: Fixed versus random effects in Poisson regression models for claim counts: A case study with motor insurance. Astin Bulletin 36(1), 285–301 (2006)Google Scholar
  5. 5.
    Boucher, J.-P., Denuit, M.: Duration dependence models for claim counts. Deutsche Gesellschaft für Versicherungsmathematik (Ger. Actuar. Bull.) 28(1), 29–45 (2007)Google Scholar
  6. 6.
    Boucher, J.-P., Denuit, M., Guillen, M.: Models of insurance claim counts with time dependence based on generalization of Poisson and negative binomial distribuitions. Variance 2(1), 135–162 (2008)Google Scholar
  7. 7.
    Boucher, J.-P., Denuit, M., Guillen, M.: Number of accidents or number of claims? An approach with zero-inflated poisson models for panel data. J. Risk Insur. 76(4), 821–845 (2009)Google Scholar
  8. 8.
    Boucher, J.-P., Guillén, M.: A survey on models for panel count data with applications to insurance. Revista de la Real Academia de Ciencias Exactas, Fisicas y Naturales 103(2), 277–295 (2009)Google Scholar
  9. 9.
    Broström, G., Holmberg, H.: glmmML: Generalized linear models with clustering. R package version 0.81-8 (2011)Google Scholar
  10. 10.
    Fawcett, T.: An introduction to Roc analysis. Pattern Recogn. Lett. 19, 861–874 (2006)Google Scholar
  11. 11.
    Jong, P.D., Heller, G.Z.: Generalized Linear Models for Insurance Data, ch. 5.5, Cambridge University Press, Cambridge (2008)Google Scholar
  12. 12.
    R Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing. Vienna, Austria (2012). ISBN 3-900051-07-0. http://www.R-project.org
  13. 13.
    Rönnegård, L., Shen, X., Alam, M.: The hglm package. R package version 1.2 (2011)Google Scholar
  14. 14.
    Tomberlin, T.J.: Predicting accident frequencies for drivers classified by two factors. J. Am. Stat. Assoc. 83(402), 309–321 (1988)CrossRefGoogle Scholar
  15. 15.
    Yau, K.W., Yip, K.C.H., Yuen, H.K.: Modelling repeated insurance claim frequency data using the generalized linear mixed model. J. Appl. Stat. 30(8), 857–865 (2003). doi: 10.1080/0266476032000075949
  16. 16.
    Zhang, H., Lu, N., Feng, C., Thurston, S.W., Xia, Y., Zhu, L., Tu, X.M.: On fitting generalized mixed-effects models for binary responses using different statistical packages. Stat. Med. 30(20), 2562–2572 (2011)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Clara-Cecilie Günther
    • 1
    Email author
  • Ingunn Fride Tvete
    • 1
  • Kjersti Aas
    • 1
  • Jørgen Andreas Hagen
    • 2
  • Lars Kvifte
    • 2
  • Ørnulf Borgan
    • 3
  1. 1.Norwegian Computing CenterOsloNorway
  2. 2.GjensidigeOsloNorway
  3. 3.University of OsloOsloNorway

Personalised recommendations