Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Predictive analysis in insurance: An application of generalized linear mixed models

  • Rosy Oh (Department of Mathematics, Korea Military Academy) ;
  • Nayoung Woo (Department of Statistics, Ewha Womans University) ;
  • Jae Keun Yoo (Department of Statistics, Ewha Womans University) ;
  • Jae Youn Ahn (Department of Statistics, Ewha Womans University)
  • Received : 2023.02.07
  • Accepted : 2023.07.11
  • Published : 2023.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Generalized linear models and generalized linear mixed models (GLMMs) are fundamental tools for predictive analyses. In insurance, GLMMs are particularly important, because they provide not only a tool for prediction but also a theoretical justification for setting premiums. Although thousands of resources are available for introducing GLMMs as a classical and fundamental tool in statistical analysis, few resources seem to be available for the insurance industry. This study targets insurance professionals already familiar with basic actuarial mathematics and explains GLMMs and their linkage with classical actuarial pricing tools, such as the Buhlmann premium method. Focus of the study is mainly on the modeling aspect of GLMMs and their application to pricing, while avoiding technical issues related to statistical estimation, which can be automatically handled by most statistical software.

Keywords

Acknowledgement

Rosy Oh was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) and was funded by the Ministry of Education (NRF-2020R1I1A1A01067376). This research was supported by the Korean Risk Management Society. Jae Youn Ahn was partly supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government(MSIT) (RS-2023-00217022) and an Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korean government (MSIT) (RS-2022-00155966). The authors thank Ruhuan Feng (University of Illinois Urbana-Champaign) and Emiliano Valdez (University of Connecticut) for their comments and advice on this research.

References

  1. Antonio K and Beirlant J (2007). Actuarial statistics with generalized linear mixed models, Insurance: Mathematics and Economics, 40, 58-76. https://doi.org/10.1016/j.insmatheco.2006.02.013
  2. Breslow NE and Clayton DG (1993). Approximate inference in generalized linear mixed models, Journal of the American Statistical Association, 88, 9-25. https://doi.org/10.1080/01621459.1993.10594284
  3. Buhlmann H and Gisler A (2005). A Course in Credibility Theory and Its Applications (Vol. 317), Berlin, Springer.
  4. Embrechts P (2009). Copulas: A personal view, Journal of Risk and Insurance, 76, 639-650. https://doi.org/10.1111/j.1539-6975.2009.01310.x
  5. Frees EW, Lee G, and Yang L (2016). Multivariate frequency-severity regression models in insurance, Risks, 4, 4.
  6. Frees EW and Valdez EA (1998). Understanding relationships using copulas, North American Actuarial Journal, 2, 1-25. https://doi.org/10.1080/10920277.1998.10595667
  7. Golub GH and Welsch JH (1969). Calculation of gauss quadrature rules, Mathematics of Computation, 23, 221-230. https://doi.org/10.1090/S0025-5718-69-99647-1
  8. Krupskii P and Joe H (2013). Factor copula models for multivariate data, Journal of Multivariate Analysis, 120, 85-101. https://doi.org/10.1016/j.jmva.2013.05.001
  9. Lai TL and Sun KH (2012). Evolutionary credibility theory: A generalized linear mixed modeling approach, North American Actuarial Journal, 16, 273-284. https://doi.org/10.1080/10920277.2012.10590641
  10. Laplace PS (1986). Memoir on the probability of the causes of events, Statistical Science, 1, 364-378. https://doi.org/10.1214/ss/1177013621
  11. Lee W, Kim J, and Ahn JY (2020). The poisson random e ect model for experience ratemaking: Limitations and alternative solutions, Insurance: Mathematics and Economics, 91, 26-36. https://doi.org/10.1016/j.insmatheco.2019.12.004
  12. Lee Y and Nelder JA (1996). Hierarchical generalized linear models, Journal of the Royal Statistical Society: Series B (Methodological), 58, 619-656. https://doi.org/10.1111/j.2517-6161.1996.tb02105.x
  13. McCullagh P and Nelder JA (1989). Generalized Linear Models (2nd ed), Chapman and Hall, London.
  14. Mowbray AH (1914). How extensive a payroll exposure is necessary to give a dependable pure premium, Proceedings of the Casualty Actuarial Society, 1, 24-30.
  15. Nelder JA and Verrall RJ (1997). Credibility theory and generalized linear models, ASTIN Bulletin: The Journal of the IAA, 27, 71-82. https://doi.org/10.2143/AST.27.1.563206
  16. Oh R, Shi P, and Ahn JY (2020). Bonus-malus premiums under the dependent frequency-severity modeling, Scandinavian Actuarial Journal, 2020, 172-195. https://doi.org/10.1080/03461238.2019.1655477
  17. Ohlsson E (2008). Combining generalized linear models and credibility models in practice, Scandinavian Actuarial Journal, 2008, 301-314. https://doi.org/10.1080/03461230701878612
  18. Ronnegard L, Shen X, and Alam M (2010). hglm: A package for fitting hierarchical generalized linear models, The R Journal, 2, 20-28. https://doi.org/10.32614/RJ-2010-009
  19. Whitney A (1918). The theory of experience rating, Proceedings of the Casualty Actuarial Society, 4, 274-292.
  20. Wuthrich MV (2021). From Generalized Linear Models to Neural Networks, and Back. [S.l.]: SSRN, Available from: https://ssrn.com/abstract=3491790
  21. Zimmer DM (2018). The heterogeneous impact of insurance on health care demand among young adults: A panel data analysis, Journal of Applied Statistics, 45, 1277-1291. https://doi.org/10.1080/02664763.2017.1369497