×

Sarmanov family of multivariate distributions for bivariate dynamic claim counts model. (English) Zbl 1373.62507

Summary: To predict future claims, it is well-known that the most recent claims are more predictive than older ones. However, classic panel data models for claim counts, such as the multivariate negative binomial distribution, do not put any time weight on past claims. More complex models can be used to consider this property, but often need numerical procedures to estimate parameters. When we want to add a dependence between different claim count types, the task would be even more difficult to handle. In this paper, we propose a bivariate dynamic model for claim counts, where past claims experience of a given claim type is used to better predict the other type of claims. This new bivariate dynamic distribution for claim counts is based on random effects that come from the Sarmanov family of multivariate distributions. To obtain a proper dynamic distribution based on this kind of bivariate priors, an approximation of the posterior distribution of the random effects is proposed. The resulting model can be seen as an extension of the dynamic heterogeneity model described in [C. Bolancé et al., “Greatest accuracy credibility with dynamic heterogeneity: the Harvey-Fernandes model”, Belg. Actuar. Bull. 7, No. 1, 14–18 (2007)]. We apply this model to two samples of data from a major Canadian insurance company, where we show that the proposed model is one of the best models to adjust the data. We also show that the proposed model allows more flexibility in computing predictive premiums because closed-form expressions can be easily derived for the predictive distribution, the moments and the predictive moments.

MSC:

62P05 Applications of statistics to actuarial sciences and financial mathematics
91B30 Risk theory, insurance (MSC2010)
PDFBibTeX XMLCite
Full Text: DOI Link

References:

[1] Abdallah, A.; Boucher, J.-P.; Cossette, H.; Trufin, J., Sarmanov family of bivariate distributions for multivariate loss reserving analysis, N. Am. Actuar. J., 20, 3 (2015)
[2] Bolancé, C.; Bahraoui, Z.; Artís, M., Quantifying the risk using copulae with nonparametric marginal, Insurance Math. Econom., 58, 46-56 (2014) · Zbl 1304.62127
[3] Bolancé, C.; Denuit, M.; Guillén, M.; Lambert, P., Greatest accuracy credibility with dynamic heterogeneity: the Harvey-Fernandes model, Belg. Actuar. Bull., 1, 14-18 (2007)
[4] Boucher, J.-P.; Denuit, M.; Guillen, M., Risk classification for claim counts: A comparative analysis of various zero-inflated mixed Poisson and hurdle models, N. Am. Actuar. J., 11, 4, 110-131 (2007) · Zbl 1480.91187
[5] Boucher, J.-P.; Denuit, M.; Guillen, M., Models of insurance claim counts with time dependence based on generalisation of Poisson and negative binomial distributions, Variance, 2, 1, 135-162 (2008)
[6] Boucher, J.-P.; Inoussa, R., A posteriori ratemaking with panel data, ASTIN Bull., 44, 3, 587-612 (2014) · Zbl 1431.91319
[7] Cohen, L., Probability distributions with given multivariate marginals, J. Math. Phys., 25, 2402-2403 (1984) · Zbl 0566.60013
[8] Danaher, P.; Smith, M., Modeling multivariate distributions using copulas: Applications in marketing, Mark. Sci., 30, 1, 4-21 (2011)
[9] Denuit, M.; Marechal, X.; Pitrebois, S.; Walhin, J.-F., Actuarial Modelling of Claim Counts: Risk Classification, Credibility and Bonus-Malus Scales (2007), Wiley: Wiley New York · Zbl 1168.91001
[10] Frees, E.; Valdez, E., Hierarchical insurance claims modeling, J. Amer. Statist. Assoc., 103, 484, 1457-1469 (2008) · Zbl 1286.62087
[11] Gerber, H.; Jones, D., Cedibility formulas of the updating type, (Kahn, P. M., Credibility (1975), Academic Press: Academic Press New York), 89-105
[12] Gourieroux, C.; Monfort, A.; Trognon, A., Pseudo-maximum likelihood methods: Theory, Econometrica, 52, 4, 681-700 (1984) · Zbl 0575.62031
[13] Harvey, A.; Fernandes, C., Time series models for count or qualitative observations, J. Bus. Econom. Statist., 7, 407-422 (1989)
[14] Hernández-Bastida, A.; Fernández-Sánchez, A Sarmanov family with beta and gamma marginal distributions: An application to the Bayes premium in a collective risk model, Stat. Methods Appl., 21, 4, 91-409 (2012) · Zbl 1332.62042
[15] Jewell, W., The use of collateral data in credibility theory: A Hierarchical model, G. Ist. Ital. Attuari, 38, 1-16 (1975) · Zbl 0392.62086
[16] Jung, R.; Liesenfeld, R., Estimating time series models for count data using effcient importance sampling, Allg. Stati. Arch., 85, 387-407 (2001) · Zbl 1100.62086
[17] Lee, M.-L. T., Properties and applications of the Sarmanov family of bivariate distributions, Comm. Statist. Theory Methods, 25, 6, 1207-1222 (1996) · Zbl 0875.62205
[18] McCullagh, P.; Nelder, J., Generalized Linear Models (1989), Chapman and Hall: Chapman and Hall Boca Raton, FL · Zbl 0744.62098
[20] Pinquet, J., Designing optimal Bonus-Malus systems from different types of claims, ASTIN Bull., 28, 205-229 (1998) · Zbl 1162.91430
[21] Pinquet, J.; Guillen, M.; Bolance, C., Allowance for age of claims in Bonus-Malus systems, ASTIN Bull., 31, 337-348 (2001) · Zbl 1098.91544
[22] Purcaru, O.; Denuit, M., On the dependence induced by frequency credibility models, Belg. Actuar. Bull., 2, 1, 73-79 (2002)
[23] Sarmanov, O., Generalized normal correlation and two-dimensional frechet classes, Dokl. Sov. Math., Tom 168, 596-599 (1966) · Zbl 0203.20001
[24] Schweidel, D.; Fader, P.; Bradlow, E., A bivariate timing model of customer acquisition and retention, Mark. Sci., 27, 5, 829-843 (2008)
[25] Self, S. G.; Liang, K. Y., Asymptotic properties of maximum likelihood estimators and likelihood ratio tests under nonstandard conditions, J. Amer. Statist. Assoc., 82, 398, 605-610 (1987) · Zbl 0639.62020
[26] Shi, P.; Valdez, E., Longitudinal modeling of insurance claim counts using jitters, Scand. Actuar. J., 2, 159-179 (2014) · Zbl 1401.91195
[27] Xu, S.; Jones, R.; Grunwald, G., Analysis of longitudinal count data with serial correlation, Biometrika J., 49, 3, 416-428 (2007) · Zbl 1442.62707
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. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.