DOI QR코드

DOI QR Code

Estimation of Car Insurance Loss Ratio Using the Peaks over Threshold Method

POT방법론을 이용한 자동차보험 손해율 추정

  • Kim, S.Y. (Department of Statistics, Ewha Womans University) ;
  • Song, J. (Department of Statistics, Ewha Womans University)
  • 김수영 (이화여자대학교 통계학과) ;
  • 송종우 (이화여자대학교 통계학과)
  • Received : 20111100
  • Accepted : 20121200
  • Published : 2012.02.29

Abstract

In car insurance, the loss ratio is the ratio of total losses paid out in claims divided by the total earned premiums. In order to minimize the loss to the insurance company, estimating extreme quantiles of loss ratio distribution is necessary because the loss ratio has essential prot and loss information. Like other types of insurance related datasets, the distribution of the loss ratio has heavy-tailed distribution. The Peaks over Threshold(POT) and the Hill estimator are commonly used to estimate extreme quantiles for heavy-tailed distribution. This article compares and analyzes the performances of various kinds of parameter estimating methods by using a simulation and the real loss ratio of car insurance data. In addition, we estimate extreme quantiles using the Hill estimator. As a result, the simulation and the loss ratio data applications demonstrate that the POT method estimates quantiles more accurately than the Hill estimation method in most cases. Moreover, MLE, Zhang, NLS-2 methods show the best performances among the methods of the GPD parameters estimation.

자동차보험의 손해율이란 지급보험금의 수입보험료에 대한 비율을 의미한다. 손해율이 매우 큰 값을 갖는 대형손실이 일어나는 경우에는 보험회사의 재무적인 부분에 큰 악영향을 미치게 된다. 따라서 보험회사가 이에 대비할 수 있도록 하기 위하여 손해율의 극단 분위수(extreme quantile)를 추정하는 것은 매우 중요한 일이다. 다른 종류의 보험 관련 데이터와 같이 손해율의 분포는 오른쪽으로 긴 꼬리를 갖는 두꺼운 꼬리분포(heavy-tailed distribution)를 갖는다. 이런 자료에서 극단 분위수룰 추정하기 위하여 가장 많이 사용되는 방법론은 POT(Peaks over threshold)와 Hill 추정(Hill estimation)이다. 본 논문에서는 일반화파레토분포(generalized Pareto distribution; GPD)의 다양한 모수추정방법론의 성능을 모의실험과 실제 손해율 데이터를 사용하여 비교, 분석하였다. 또한 Hill 추정치를 사용하여 극단 분위수를 추정하였다. 그 결과 대부분의 경우에 POT 방법론이 Hill 추정치를 이용한 방법보다 정확한 분위수를 추정하였고, 모수추정방법론 중에서는 MLE, Zhang, NLS-2 방법론이 가장 좋은 결과를 보여주었다.

Keywords

References

  1. Balkema, A. and de Haan, L. (1974). Residual life time at great age, Annals of Probability, 2, 792-804. https://doi.org/10.1214/aop/1176996548
  2. Beirlant, J., Teugels, J. and Vynckier, P. (1996). Practical analysis of extreme values, Leuven University Press, Leuven.
  3. Emvrechts, P., Kluppelberg, C. and Mikosch, T. (1997). Modeling Extremal Events for Insurance and Finance, Springer Verlag, Berlin.
  4. Fisher, R. and Tippett, L. (1928). Limiting forms of the frequency distribution of the largest or smallest member of a sample, Proceedings of the Cambridge Philosophical Society, 24, 180-190. https://doi.org/10.1017/S0305004100015681
  5. Hill, B. M. (1975). A simple general approach to inference about the tail of a distribution, Annals of Statistics, 3, 1163-1174. https://doi.org/10.1214/aos/1176343247
  6. Hogg, R. and Klugman, S. (1984). Loss Distributions, Wiley, New York.
  7. McNeil, A. J. and Saladin, T. (1997). The Peaks over thresholds method for estimating high quantiles of loss distribution, Proceedings of 28th international ASTIN Colloquium.
  8. Pickands, J. (1975). Statistical inference using extreme order statistics, Annals of Statistics, 3, 119-131. https://doi.org/10.1214/aos/1176343003
  9. Song, J. and Song, S. (2011). A quantile estimation for massive data with generalized pareto distribution, Computational Statistics and Data Analysis, 56, 143-150.
  10. Weissman, I. (1978). Estimation of parameters and larger quantile based on the k largest observations, Journal of the American Statistical Association, 73, 812-815.
  11. Zhang, J. (2007). Likelihood moment estimation for the generalized pareto distribution, Australian and New Zealand Journal of Statistics, 49, 69-77. https://doi.org/10.1111/j.1467-842X.2006.00464.x
  12. Zhang, J. (2010). Improving on estimation for the generalized pareto distribution, Technometrics, 52, 335-339. https://doi.org/10.1198/TECH.2010.09206