Abstract
We are interested in the approximation of the ruin probability of a classical risk model using the strong stability method. Particularly, we study the sensitivity of the stability bound for ruin probabilities of two risk models to approach (a simpler ideal model and a complex real one, which must be close in some sense) regarding to different large claims (heavy-tailed distributions). In a first case, we study the impact of the tail of some claim distributions on the quality of this approximation using the strong stability of a Markov chain. In a second case, we look at the sensitivity of the stability bound for the ruin probability regarding to different large claims, using two versions of the strong stability method: strong stability of a Markov chain and strong stability of a Lindley process. In both cases, comparative studies based on numerical examples and simulation results, involving different heavy-tailed distributions, are performed.
Similar content being viewed by others
References
Aïssani D, Kartashov NV (1983) Ergodicity and stability of Markov chains with respect to operator topology in the space of transition kernels. Doklady Akademii Nauk Ukrainskoi SSR, Series A 11:3–5
Aïssani D, Benouaret Z (2010) Modèles de risque et files d’attente: la méthode de stabilité forte. Afrika Statistika 5(1):210–218
Asmussen S, Albrecher H (2010) Ruin probabilities (Second Edition). Advanced series on statistical science & applied probability, vol 14, World Scientific Publishing, Singapore, p 620
Asmussen S, Kella O (1996) Rate modulation in dams and ruin problems. J Appl Probab 33:523–535
Asmussen S, Sigman K (1996) Monotone stochastic recursions and their duals. Probab Eng Inf Sci 10:1–20
Badila ES, Boxma OJ, Resing AC (2014) Queues and risk processes with dependencies. Stoch Model 30(3):390–419
Bareche A, Cherfaoui M, Aïssani D (2015) Quality of the approximation of ruin probabilities regarding to large claims. In: Le Thi HA et al (eds) Advanced computational methods for knowledge engineering, Advances in intelligent systems and computing, vol 358. Springer, Switzerland, pp 119–126, DOI https://doi.org/10.1007/978-3-319-17996-4_11
Beirlant J, Rachev ST (1987) The problems of stability in insurance mathematics. Insurance Math and Econom 6:179–188
Benouaret Z, Aïssani D (2010) Strong stability in a two-dimensional classical risk model with independent claims. Scand Actuar J 2:83–92
Bolancé C, Guillen M, Nielsen JP (2003) Kernel density estimation of actuarial loss functions. Insurance: Math and Econom 32:19–36
Buch-Larsen T, Nielsen JP, Guillen M, Bolancé C (2005) Kernel density estimation for heavy-tailed distribution using the Champernowne transformation. Statistics 6:503–518
Chen SX (1999) Beta kernel estimators for density functions. Comput Stat Data Anal 31:131–145
Coles S (2001) An introduction to statistical modelling of extreme values. Springer, Berlin
Embrechts P, Klueppelberg C, Mikosch T (1997) Modelling extremal events for finance and insurance. Springer, Heildelberg
Embrechts P, Veraverbeke N (1982) Estimates for the probability of ruin with special emphasis on the possibility of large claims. Insurance: Math and Econom 1:55–72
Enikeeva F, Kalashnikov V, Rusaityte D (2001) Continuity estimates for ruin probabilities. Scand Actuar J 1:18–39
Gouriéroux C, Montfort A (2006) (non) consistency of the beta kernel estimator for recovery rate distribution. Working Paper 2006–31, Center for Research in Economics and Statistics (CREST)
Jansen S (2014) On the notion(s) of duality for Markov processes. Probab Surv 11:59–120
Ji L, Zhang C (2014) A duality result for the generalized erlang risk model. Risks 2:456–466
Kalashnikov V (1978) Qualitative analysis of the behavior of complex systems by the test functions method. Moscow: Nauka, Russian
Kalashnikov V (1999) Bounds for ruin probabilities in the presence of large claims and their comparison. North American Actuarial Journal 3(2):116–128
Kalashnikov V (2000) The stability concept for stochastic risk models, Working Paper Nr 166, Laboratory of Actuarial Mathematics, University of Copenhagen
Kalashnikov V, Tsitsiashvili GSh (1973) On the stability of queueing systems with respect to disturbances of their distribution functions. Eng Cybern 10:211–217
Kartashov NV (1986) Strongly stable Markov chains, stability problems for stochastic models (1981a), “Vsesoyus. Nauchno-Issled. Inst Sistem Issled”, Moscow, 54–59 English translation, vol 34
Kartashov NV (1996) Strong stable Markov chains. TbiMC Scientific Publishers, VSPV Utrecht
Kolokoltsov V, Lee R (2013) Stochastic duality of Markov processes: a study via generators. Stoch Anal Appl 31(6):992–1023
Konstantinidis DG (1999) Comparison of ruin probability estimates in the presence of heavy tails. J Math Sci 93(4):552–562
Konstantinidis DG (2007) Risk models with extremal subexponentiality. Brazilian Journal of Probability And Statistics, Brazilian Statistical Association 21:63–83
Mitrophanov AY (2005) Sensitivity and convergence of uniformly ergodic Markov chains. J Appl Probab 42:1003–1014
Mouhoubi Z, Aïssani D (2005) Some inequalities of the uniform ergodicity and strong stability of homogeneous Markov chains. Pliska Studia Mathematica Bulgarica 17:171–186
Panjer HH, Willmot GE (1992) Insurance risk models. The society of actuaries, Schaumburg (Illinois), p 442
Rachev ST (1991) Probability Metrics and the Stability of the Stochastic Models, Wiley series in probability and mathematical statistics - Applied probability and statistics. Wiley, New York
Rusaityte D (2001) Continuity of the ruin probability in a model with borrowing and investments, Working Paper Nr 172, Laboratory of Actuarial Mathematics, University of Copenhagen
Rusaityte D (2001) Stability bounds for ruin probabilities in a Markov modulated risk model with investments, Working Paper Nr 178, Laboratory of Actuarial Mathematics, University of Copenhagen
Thampi KK, Jacob MJ (2010) On a class of renewal queueing and risk processes. The Journal of Risk Finance 11(2):204–220
Touazi A, Benouaret Z, Aïssani D, Adjabi S (2017) Nonparametric estimation of the claim amount in the strong stability analysis of the classical risk model. Insurance: Math and Econom 74:78–83
Tsitsiashvili GSh, Konstantinides DG (2001) Supertails in risk theory. Far Eastern Mathematical Journal 2:68–76
Vatamidou E, Adan IJBF, Vlasiou M, Zwart B (2014) On the accuracy of phase-type approximations of heavy-tailed risk models. Scand Actuar J 2014(6):510–534
Zhang Z, Yang H, Yang H (2014) On a nonparametric estimator for ruin probability in the classical risk model. Scand Actuar J 4:309–338
Zolotarev V (1983) Probability metrics. Theory of Probability and its Applications 28(2):278–302
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bareche, A., Cherfaoui, M. Sensitivity of the Stability Bound for Ruin Probabilities to Claim Distributions. Methodol Comput Appl Probab 21, 1259–1281 (2019). https://doi.org/10.1007/s11009-018-9675-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11009-018-9675-7