Abstract
The problem of estimation of the heavy tail index is revisited from the point of view of truncated estimation. A class of novel estimators is introduced having guaranteed accuracy based on a sample of fixed size. The performance of these estimators is quantified both theoretically and in simulations over a host of relevant examples. It is also shown that in several cases the proposed estimators attain — within a logarithmic factor — the optimal parametric rate of convergence. The property of uniform asymptotic normality of the proposed estimators is established.
Similar content being viewed by others
References
J. Beirlant, J. L. Teugels, and P. Vynckier, Practical Analysis of Extreme Values (Leuven Univ. Press, 1996).
A. V. Dobrovidov, G. M. Koshkin, and V. A. Vasiliev, Nonparametric State Space Models (Kendrick Press, USA, 2012)
H. Drees, “Optimal Rates of Convergence for Estimates of the Extreme Value Index”, Ann. Statist. 26, 434–448 (1998).
P. Embrechts, C. Kluppelberg, and T. Mikosch, Modelling Extremal Events for Insurance and Finance (Springer, Berlin, 1997).
D. Fourdrinier, V. Konev, and S. Pergamenshchikov, “Truncated Sequential Estimation of the Parameter of a First Order Autoregressive Process with Dependent Noises”, Math. Methods Statist. 18 (1), 43–58 (2009).
C. M. Goldie and R. L. Smith, “Slow Variation with Remainder: Theory and Applications”, Quarterly J. Math. 38, 45–71 (1987).
I. Grama and V. Spokoiny, “Statistics of Extremes by Oracle Estimation”, Ann. Statist. 36, 1619–1648 (2008).
P. E. Greenwood and A. N. Shiryaev, “On Uniform Weak Convergence of Semimartingales with Application to Estimation of the Parameter of an Autoregressive Model of the First Order”, in Statistics and Control of Stochastic Processes, Ed. by A. N. Shiryaev (Nauka, Moscow, 1989), pp. 40–48 [in Russian].
B. M. Hill, “A Simple General Approach to Inference about the Tail of a Distribution”, Ann. Statist. 3 1163–1174 (1975).
R. V. Hogg and S. A. Klugman, Loss Distributions (Wiley, New York, 1984).
V. V. Konev and S. M. Pergamenshchikov, “Truncated sequential estimation of the parameters in random regression”, Sequential Anal. 9, 19–41 (1990).
V. V. Konev and S. M. Pergamenshchikov, “On Truncated Sequential Estimation of the Drifting Parameter Mean in the First Order Autoregressive Models”, Sequential Anal. 9, 193–216 (1990).
N. Markovich, Nonparametric Analysis of Univariate Heavy-Tailed Data Research and Practice (Wiley, New York, 2007).
P. W. Mikulski and M. J. Monsour, “Optimality of the Maximum Likelihood Estimator in First-Order Autoregressive Processes”, J. Time Series Anal. 8 (3), 237–253 (1991).
S. Y. Novak, “On the Distribution of the Ratio of Sums of Random Variables”, Theory Probab. Appl. 41, 479–503 (1996).
S. Y. Novak, “On Self-Normalized Sums”, Math. Methods Statist. 9, 415–436 (2000)
S. Y. Novak, “Inference of Heavy Tails from Dependent Data”, Sib. Adv. Math. 12 73–96 (2002).
S. Y. Novak, Extreme Value Methods with Applications to Finance (Chapman and Hall/CRC Press, London, 2011), ISBN 9781439835746.
D. N. Politis and V. A. Vasiliev, “Sequential Kernel Estimation of a Multivariate Regression Function”, in Proc. IX Internat. Conf. ‘System Identification and Control Problems’, SICPRO’12. Moscow, 30 January–2 February, 2012 (Trapeznikov Institute of Control Sciences, Moscow, 2012a), pp. 996–1009.
D. N. Politis and V. A. Vasiliev, “Non-parametric Sequential Estimation of a Regression Function Based on Dependent Observations”, in Sequential Analysis: Design Methods and Applications, 32 (3), 243–266 (2013). https://doi.org/www.tandfonline.com/doi/full/10.1080/07474946.2013.803398.
H. Ramlau-Hansen, “A Solvency Study in Non-Life Insurance”, Scand. Actuar. J. 80, 3–34 (1988).
S. I. Resnick and C. Starica, “Smoothing the Moment Estimate of the Extreme Value Parameter”, Extremes 1, 263–294 (1999).
J. Roll, A. Nazin, and L. Ljung, “A Non-Asymptotic Approach to Local Modelling”, The 41st IEEE CDC, Las Vegas, Nevada, USA, 10–13 Dec. 2002. (2002) (Regular paper).
J. Roll, A. Nazin, and L. Ljung, “Nonlinear System Identification Via Direct Weight Optimization”, Automatica. Journal of IFAC. Special Issue on "Data-Based Modelling and System Identification" 41 (3), 475–490 (2005). Predocumentation is available at https://doi.org/www.control.isy.liu.se/research/reports/2005/2696.pdf
A. N. Shiryaev and V. G. Spokoiny, Statistical Experiments and Decisions. Asymptotic Theory (World Scientific, Singapore, New Jersey, London, Hong Kong, 2000).
V. Vasiliev, “A Truncated Estimation Method with Guaranteed Accuracy”, Ann. Inst. Statist. Math. 66 141–163 (2014).
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Politis, D.N., Vasiliev, V.A. & Vorobeychikov, S.E. Truncated Estimation of Ratio Statistics with Application to Heavy Tail Distributions. Math. Meth. Stat. 27, 226–243 (2018). https://doi.org/10.3103/S1066530718030043
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1066530718030043
Keywords
- heavy tails
- parameter estimation
- Pareto type distributions
- guaranteed accuracy
- finite sample size
- optimal convergence rate