A gamma kernel density estimation for insurance loss data. (English) Zbl 1290.62099

Summary: Fitting insurance loss data can be challenging because of their non-negativity, asymmetry, skewness, and possible multi-modality. Though many parametric models have been used in the actuarial literature, these difficulties call for more flexible models for actuarial applications. In this paper, we propose a new class of gamma kernel density estimators (GKDEs) based on the gamma density. We prove that the density of the proposed model converges to that of any loss random variable which is non-negative and continuous, and establish its rate of convergence, under some technical conditions. The proposed model has several advantages over the existing gamma kernel class by S. X. Chen [Ann. Inst. Stat. Math. 52, No. 3, 471–480 (2000; Zbl 0960.62038)] in that it is a valid density for any finite sample and has standard distributional quantities, such as the moments, the conditional tail moments, and the compound distribution with GKDE claim amounts, in analytic form. The model is also a competing model of the Erlang mixture by S. C. K. Lee and X. S. Lin [“Modeling and evaluating insurance losses via mixtures of Erlang distributions”, N. Am. Actuar. J. 14, No. 1, 107–130 (2010; doi:10.1080/10920277.2010.10597580)] in its flexibility, but with a straightforward implementation and optimization. As numerical examples, we fit the gamma kernel density estimator to actual insurance data and find that the proposed model gives adequate results compared to the Erlang mixture and the Phase-type models.


62P05 Applications of statistics to actuarial sciences and financial mathematics
62G07 Density estimation
91B30 Risk theory, insurance (MSC2010)


Zbl 0960.62038


EMpht; KernSmooth
Full Text: DOI


[1] Ahn, S.; Kim, J. H.T.; Ramaswami, V., A new class of models for heavy tailed distributions in finance and insurance risk, Insurance: Mathematics & Economics, 51, 43-52, (2012) · Zbl 1284.60024
[2] Asmussen, S.; Nerman, O.; Olsson, M., Fitting phase-type distributions via the EM algorithm, Scandinavian Journal of Statistics, 23, 4, 419-441, (1996) · Zbl 0898.62104
[3] Bolance, C.; Guillen, M.; Nielsen, J. P., Kernel density estimation of actuarial loss functions, Insurance: Mathematics & Economics, 32, 1, 19-36, (2003) · Zbl 1024.62041
[4] Bolancé, C.; Guillén, M.; Nielsen, J., Inverse beta transformation in kernel density estimation, Statistics & Probability Letters, 78, 13, 1757-1764, (2008) · Zbl 1147.62323
[5] Braga-Neto, U. M.; Dougherty, E. R., Is cross-validation valid for small-sample microarray classification?, Bioinformatics, 20, 3, 374-380, (2004)
[6] Buch-Larsen, T.; Nielsen, J. P.; Guillén, M.; Bolancé, C., Kernel density estimation for heavy-tailed distributions using the champernowne transformation, Statistics, 39, 6, 503-518, (2005) · Zbl 1095.62040
[7] Chen, S., Beta kernel estimators for density functions, Computational Statistics & Data Analysis, 31, 2, 131-145, (1999) · Zbl 0935.62042
[8] Chen, S., Probability density function estimation using gamma kernels, Annals of the Institute of Statistical Mathematics, 52, 3, 471-480, (2000) · Zbl 0960.62038
[9] Efron, B., Estimating the error rate of a prediction rule: improvement on cross-validation, Journal of the American Statistical Association, 78, 382, 316-331, (1983) · Zbl 0543.62079
[10] Embrechts, P.; Kluppelberg, C.; Mikosch, T., Modelling extremal events, (1997), Springer New York · Zbl 0873.62116
[11] Erdélyi, A.; Magnus, W.; Oberhettinger, F.; Tricomi, F. G., Bateman manuscript project, Higher Transcendental Functions, vol. III, (1953), McGraw-Hill Book Co. New York
[12] Klugman, S.; Panjer, H.; Willmot, G., Loss models, (2008), John Wiley New York · Zbl 1159.62070
[13] Landsman, Z.; Valdez, E. A., Tail conditional expectations for elliptical distributions, North American Actuarial Journal, 7, 4, (2003) · Zbl 1084.62512
[14] Landsman, Z.; Valdez, E., Tail conditional expectations for exponential dispersion models, ASTIN Bulletin, 35, 1, 189-209, (2005) · Zbl 1099.62122
[15] Lee, M.; Ahn, J.; Jeon, Y., HDLSS discrimination with adaptive data piling, Journal of Computational and Graphical Statistics, 22, 2, 433-451, (2013)
[16] Lee, S.; Lin, X. S., Modeling and evaluating insurance losses via mixtures of Erlang distributions, North American Actuarial Journal, 14, 1, 107, (2010)
[17] Lin, X.; Liu, X., Markov aging process and phase-type law of mortality, North American Actuarial Journal, 11, 4, 92, (2007)
[18] Lin, X.; Willmot, G., The moments of the time of ruin, the surplus before ruin, and the deficit at ruin, Insurance: Mathematics & Economics, 27, 1, 19-44, (2000) · Zbl 0971.91031
[19] McNeil, A. J.; Frey, R.; Embrechts, P., Quantitative risk management, (2005), Princeton University Press New Jersey · Zbl 1089.91037
[20] Pflug, G.; Römisch, W., Modeling, measuring and managing risk, (2007), World Scientific · Zbl 1153.91023
[21] Pitacco, E.; Denuit, M.; Haberman, S.; Olivieri, A., Modelling longevity dynamics for pensions and annuity business, (2009), Oxford University Press USA · Zbl 1163.91005
[22] Rempala, G. A.; Derrig, R. A., Modeling hidden exposures in claim severity via the EM algorithm, North American Actuarial Journal, 9, 2, 108-128, (2003) · Zbl 1085.62515
[23] Scaillet, O., Density estimation using inverse and reciprocal inverse Gaussian kernels, Nonparametric Statistics, 16, 1-2, 217-226, (2004) · Zbl 1049.62038
[24] Silverman, B. W., Density estimation for statistics and data analysis, (1986), Chapman and Hall London · Zbl 0617.62042
[25] Simonoff, J., Smoothing methods in statistics, (1996), Springer New York · Zbl 0859.62035
[26] Tijms, H., Stochastic models: an algorithmic approach, (1994), John Wiley & Sons New York · Zbl 0838.60075
[27] Valdez, E. A., Tail conditional variance for elliptically contoured distributions, Belgian Actuarial Bulletin, 5, 1, 26-36, (2005) · Zbl 1398.62329
[28] Wand, M. P.; Jones, M. C., Kernel smoothing, (1995), Chapman and Hall London · Zbl 0854.62043
[29] Wand, M. P.; Marron, J. S.; Ruppert, D., Transformations in density estimation (with discussion), Journal of the American Statistical Association, 86, 343-361, (1991) · Zbl 0742.62046
[30] Wang, J.; Zhou, H.; Zhou, M.; Li, L., A general model for long-tailed network traffic approximation, Journal of Supercomputing, 38, 2, 155-172, (2006)
[31] Willmot, G.; Lin, X., Lundberg approximations for compound distributions with insurance applications, vol. 156, (2001), Springer Verlag
[32] Willmot, G. E.; Woo, J.-K., On the class of Erlang mixtures with risk theoretic applications, North American Actuarial Journal, 11, 2, 99-115, (2007)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.