Robust estimator of conditional tail expectation of Pareto-type distribution. (English) Zbl 1458.62104
Summary: In this paper, we use the extreme value index estimator, called the t-Hill, to derive a robust estimator of conditional tail expectation (CTE) in the case of heavy-tailed losses. The CTE is rapidly turning into the favored measure for statutory assessment of the balance sheet at whatever point true stochastic techniques are utilized to fix the provisions for risks. Under the extreme value methodology, we prove the asymptotic normality of the robust nonparametric conditional tail expectation estimator when the loss variable follows any distribution with infinite second moment. In addition, the numerical performance of our new estimator is studied and compared to a well-established estimator, with favorable results.
MSC:
| 62G32 | Statistics of extreme values; tail inference |
| 62H12 | Estimation in multivariate analysis |
| 62G35 | Nonparametric robustness |
Keywords:
conditional tail expectation; t-Hill estimator; tail index; heavy-tailed distribution; robust estimatorReferences:
| [1] | Beran, J.; Schell, D.; Stehlík, M., The harmonic moment tail index estimator: asymptotic distribution and robustness, Ann Inst Stat Math, 66, 1, 193-220 (2014) · Zbl 1281.62123 · doi:10.1007/s10463-013-0412-2 |
| [2] | Brahimi, B.; Kenioua, Z., Robust estimator of distortion risk premiums for heavy-tailed losses, Afrika Stat, 11, 1, 869-882 (2016) · Zbl 1337.62089 · doi:10.16929/as/2016.869.80 |
| [3] | Brazauskas, V.; Jones, BL; Puri, ML; Zitikis, R., Estimating conditional tail expectation with actuarial applications in view, J Stat Plan Inference, 138, 11, 3590-3604 (2008) · Zbl 1152.62027 · doi:10.1016/j.jspi.2005.11.011 |
| [4] | Csörgő, M.; Csörgő, S.; Horváth, L.; Mason, DM, Weighted empirical and quantile processes, Ann Prob, 14, 31-85 (1986) · Zbl 0589.60029 · doi:10.1214/aop/1176992617 |
| [5] | Deme, E.; Girard, S.; Guillou, A., Reduced-bias estimator of the proportional hazard premium for heavy-tailed distributions, Insur: Math Econ, 52, 3, 550-559 (2013) · Zbl 1284.62211 |
| [6] | Denuit, M.; Dhaene, J.; Goovaerts, M.; Kaas, R., Actuarial theory for dependent risks: measures, orders and models (2006), Hoboken: Wiley, Hoboken |
| [7] | Fabián Z, and Stehlík M (2009) On robust and distribution sensitive Hill like method. IFAS research report, 43 |
| [8] | Geluk, J.; De Haan, L.; Resnick, S.; Stărică, C., Second-order regular variation, convolution and the central limit theorem, Stoch Process Appl, 69, 2, 139-159 (1997) · Zbl 0913.60001 · doi:10.1016/S0304-4149(97)00042-2 |
| [9] | de Haan, L.; Resnick, S., Second-order regular variation and rates of convergence in extreme-value theory, Ann Probab, 24, 97-124 (1996) · Zbl 0862.60039 · doi:10.1214/aop/1042644709 |
| [10] | Hill, BM, A simple general approach to inference about the tail of a distribution, Ann Stat, 3, 5, 1163-1174 (1975) · Zbl 0323.62033 · doi:10.1214/aos/1176343247 |
| [11] | Jordanova, P.; Fabián, Z.; Hermann, P.; Str̆elec, L.; Rivera, A.; Girard, S.; Torres, S.; Stehlík, M., Weak properties and robustness of t-Hill estimators, Extremes, 19, 4, 591-626 (2016) · Zbl 1354.62002 · doi:10.1007/s10687-016-0256-2 |
| [12] | Jordanova, PK; Pancheva, EI, Weak asymptotic results for t-Hill estimator, Comptes rendus de l’académie bulgare des sciences, 65, 12, 1649-1656 (2012) · Zbl 1313.62026 |
| [13] | Juárez, SF; Schucany, WR, Robust and efficient estimation for the generalized Pareto distribution, Extremes, 7, 3, 237-251 (2004) · Zbl 1091.62017 · doi:10.1007/s10687-005-6475-6 |
| [14] | Kim, M.; Lee, S., Estimation of a tail index based on minimum density power divergence, J Multivar Anal, 99, 10, 2453-2471 (2008) · Zbl 1151.62321 · doi:10.1016/j.jmva.2008.02.031 |
| [15] | Necir, A.; Meraghni, D.; Meddi, F., Statistical estimate of the proportional hazard premium of loss, Scand Actuarial J, 2007, 3, 147-161 (2007) · Zbl 1150.91027 · doi:10.1080/03461230601162323 |
| [16] | Necir A, Rassoul A, Zitikis R (2010) Estimating the conditional tail expectation in the case of heavy-tailed losses. J Probab Stat, ID 596839, 17 pp · Zbl 1200.91142 |
| [17] | Peng, L.; Welsh, AH, Robust estimation of the generalized Pareto distribution, Extremes, 4, 1, 53-65 (2001) · Zbl 1008.62024 · doi:10.1023/A:1012233423407 |
| [18] | Reiss, R-D; Thomas, M., Statistical analysis of extreme values with applications to insurance, finance, hydrology and other fields (2007), Basel: Birkhauser Verlag, Basel · Zbl 1122.62036 |
| [19] | Stehlík, M.; Fabián, Z.; Střelec, L., Small sample robust testing for normality against Pareto tails, Commun Stat-Simul Comput, 41, 7, 1167-1194 (2012) · Zbl 1347.62036 · doi:10.1080/03610918.2012.625849 |
| [20] | Stehlík, M.; Potockỳ, R.; Waldl, H.; Fabián, Z., On the favorable estimation for fitting heavy tailed data, Comput Stat, 25, 3, 485-503 (2010) · Zbl 1226.62013 · doi:10.1007/s00180-010-0189-1 |
| [21] | Vandewalle, B.; Beirlant, J.; Christmann, A.; Hubert, M., A robust estimator for the tail index of Pareto-type distributions, Comput Stat Data Anal, 51, 12, 6252-6268 (2007) · Zbl 1445.62102 · doi:10.1016/j.csda.2007.01.003 |
| [22] | Weissman, I., Estimation of parameters and large quantiles based on the k largest observations, J Am Stat Assoc, 73, 364, 812-815 (1978) · Zbl 0397.62034 |
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.
