Abstract
We propose a test to distinguish between two classes of distribution tails using only higher order statistics of a sample and prove its consistency. We do not assume the corresponding distribution functions to belong to any maximum domain of attraction.
Similar content being viewed by others
References
Goldie, C.M. and Smith, R.L., Slow Variation with Remainder: Theory and Applications, Quart. J. Math. Oxford Ser. (2), 1987, vol. 38, no. 1, pp. 45–71.
Guilbaud, O., Exact Kolmogorov-type Test for Left-Truncated and/or Right-Censored Data, J. Amer. Statist. Assoc., 1988, vol. 83, no. 401, pp. 213–221.
Chernobai, A., Menn, C., Rachev, S.T., and Trück, S., Estimation of Operational Value-at-Risk in the Presence of Minimum Collection Thresholds, Tech. Report of the Univ. of California, Santa Barbara, CA, USA, 2005.
Beirlant, T., Goegebeur, Y., Teugels, J., and Segers, J., Statistics of Extremes: Theory and Applications, Hoboken, NJ: Wiley, 2004.
de Haan, L. and Ferreira, A., Extreme Value Theory: An Introduction, New York: Springer, 2006.
Gnedenko, B.V., Sur la distribution limite du terme maximum d’une série aléatoire, Ann. Math. Ser. (2), 1943, vol. 44, no. 3, pp. 423–453.
Bingham, N.H., Goldie, C.M., and Teugels, J.L., Regular Variation, Cambridge: Cambridge Univ. Press, 1987.
de Haan, L. and Resnick, S., Second-Order Regular Variation and Rates of Convergence in Extreme-Value Theory, Ann. Probab., 1996, vol. 24, no. 1, pp. 97–124.
Pickands, J., III, Statistical Inference Using Extreme Order Statistics, Ann. Statist., 1975, vol. 3, no. 1, pp. 119–131.
Hall, P., On Some Simple Estimates of an Exponent of Regular Variation, J. Roy. Statist. Soc. Ser. B, 1982, vol. 44, no. 1, pp. 37–42.
Beirlant, T. and Teugels, J.L., Asymptotics of Hill’s Estimator, Teor. Veroyatnost. i Primenen., 1986, vol. 31, no. 3, pp. 530–536 [Theory Probab. Appl. (Reprint), 1987, vol. 31, no. 3, pp. 463–469].
Martins, M.J., Estimaçao de Caudas Pesadas–Variantes ao Estimador de Hill (Heavy Tails Estimation— Variants to the Hill Estimator), PhD Thesis, Univ. of Lisbon, Portugal, 2000.
Fraga Alves, M.I., de Haan, L., and Lin, T., Estimation of the Parameter Controlling the Speed of Convergence in Extreme Value Theory, Math. Methods Statist., 2003, vol. 12, no. 2, pp. 155–176.
Drees, H., Ferreira, A., and de Haan, L., On Maximum Likelihood Estimation of the Extreme Value Index, Ann. Appl. Probab., 2004, vol. 14, no. 3, pp. 1179–1201.
Fraga Alves, M.I., Gomes, M.I., and de Haan, L., A New Class of Semi-Parametric Estimators of the Second Order Parameter, Port. Math. (N.S.), 2003, vol. 60, no. 2, pp. 193–213.
Smith, R.L., Estimating Tails of Probability Distributions, Ann. Statist., 1987, vol. 15, no. 3, pp. 1174–1207.
de Haan, L. and Sinha, A.K., Estimating the Probability of a Rare Event, Ann. Statist., 1999, vol. 27, no. 2, pp. 732–759.
Drees, H., de Haan, L., and Li, D., Approximations to the Tail Empirical Distribution Function with Application to Testing Extreme Value Conditions, J. Statist. Plann. Inference, 2006, vol. 136, no. 10, pp. 3498–3538.
Fraga Alves, I., de Haan, L., and Neves, C., A Test Procedure for Detecting Super-Heavy Tails, J. Statist. Plann. Inference, 2009, vol. 139, no. 2, pp. 213–227.
Gardes, L., Girard, S., and Guillou, A., Weibull Tail-Distributions Revisited: A New Look at Some Tail Estimators, J. Statist. Plann. Inference, 2009, vol. 141, no. 1, pp. 429–444.
Hill, B.M., A Simple General Approach to Inference about the Tail of a Distribution, Ann. Statist., 1975, vol. 3, no. 5, pp. 1163–1174.
Berred, M., Record Values and the Estimation of the Weibull Tail-Coefficient, C. R. Acad. Sci. Paris Sér. I Math., 1991, vol. 312, no. 12, pp. 943–946.
Diebolt, J., Gardes, L., Girard, S., and Guillou, A., Bias-Reduced Estimators of the Weibull Tail-Coefficient, TEST, 2008, vol. 17, no. 2, pp. 311–331.
Rodionov, I.V., Discrimination of Close Hypotheses about Distribution Tails Using Higher Order Statistics, to appear in Teor. Veroyatnost. i Primenen.
Rodionov, I.V., A Discrimination Test for Tails of Weibull-type Distributions, Teor. Veroyatnost. i Primenen., 2018, vol. 63, no. 2, pp. 402–413.
Gardes, L. and Girard, S., Comparison of Weibull Tail-Coefficient Estimators, REVSTAT, 2006, vol. 4, no. 2, pp. 163–188.
Fraga Alves, M.I. and Neves, C., Reiss and Thomas’ Automatic Selection of the Number of Extremes, Comput. Statist. Data Anal., 2004, vol. 47, no. 4, pp. 689–704.
Falk, M., Some Best Estimators for Distributions with Finite Endpoint, Statistics, 1995, vol. 27, no. 1–2, pp. 115–125.
Resnick, S.I., A Probability Path, Boston: Birkhäuser, 1999.
Mikusheva, A.E., The Law of Large Numbers and the Logarithmic Law for Arrays, Fundam. Prikl. Mat., 2000, vol. 6, no. 1, pp. 195–206.
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © I.V. Rodionov, 2018, published in Problemy Peredachi Informatsii, 2018, Vol. 54, No. 2, pp. 29–44.
Rights and permissions
About this article
Cite this article
Rodionov, I.V. On Discrimination between Classes of Distribution Tails. Probl Inf Transm 54, 124–138 (2018). https://doi.org/10.1134/S0032946018020035
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0032946018020035