Abstract
According to a celebrated result of Kesten (Acta Math 131:207–248, 1973), random difference equations have a power-law distribution tail in the asymptotic sense. Empirical evidence shows that classical estimators of tail exponent of random difference equations, such as Hill estimator, are extremely biased for larger values of tail exponents. It is argued in this work that the bias occurs because the power-tail region is too far in the tail from a practical perspective. This is supported by analysis of a few examples where a stationary distribution of random difference equation is known explicitly, and by proving a weaker form of the so-called second order regular variation of distribution tails of random difference equations, which measures deviations from the asymptotic power tail. The latter, in particular, suggests a specific second order term for a distribution tail. Estimation of tail exponents can be adapted by taking this second order term into account. One such method available in the literature is examined, and a new, simple, regression type estimator is proposed. Simulation study shows that the proposed estimator works very well. ARCH models of interest in Finance and multiplicative cascades used in Physics are considered as motivating examples throughout the work. Extension to multidimensional random difference equations with nonnegative entries is also considered.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Baek, C., Pipiras, V.: Estimation of parameters in heavy-tailed distribution when its second order tail exponent is known. Preprint. Available at http://www.stat.unc.edu/faculty/pipiras (2009)
Basrak, B., Davis, R.A., Mikosch, T.: A characterization of multivariate regular variation. Ann. Appl. Probab. 12(3), 908–920 (2002a)
Basrak, B., Davis, R.A., Mikosch, T.: Regular variation of GARCH processes. Stoch. Process. Appl. 99(1), 95–115 (2002b)
Beirlant, J., Dierckx, G., Goegebeur, Y., Matthys, G.: Tail index estimation and an exponential regression model. Extremes 2(2), 177–200 (1999)
Bingham, N.H., Goldie, C.M., Teugels, J.L.: Regular variation. In: Encyclopedia of Mathematics and its Applications, vol. 27. Cambridge University Press, Cambridge (1989)
Bollerslev, T.: Generalized autoregressive conditional heteroskedasticity. J. Econom. 31(3), 307–327 (1986)
Breiman, L.: On some limit theorems similar to the arc-sin law. Theory Probab. Appl. 10, 351–360 (1965)
Chamayou, J.-F., Letac, G.: Explicit stationary distributions for compositions of random functions and products of random matrices. J. Theoret. Probab. 4(1), 3–36 (1991)
de Haan, L., Ferreira, A.: Extreme Value Theory. Springer Series in Operations Research and Financial Engineering. Springer, New York (2006)
de Saporta, B., Guivarc’h, Y., Le Page, E.: On the multidimensional stochastic equation Y n + 1 = A n Y n + B n . Comptes Rendus Mathématique. Académie des Sciences. Paris 339(7), 499–502 (2004)
Embrechts, P., Klüppelberg, C., Mikosch, T.: Modelling Extremal Events. Springer, Berlin (1997)
Feuerverger, A., Hall, P.: Estimating a tail exponent by modelling departure from a Pareto distribution. Ann. Stat. 27(2), 760–781 (1999)
Goldie, C.M.: Implicit renewal theory and tails of solutions of random equations. Ann. Appl. Probab. 1(1), 126–166 (1991)
Gomes, M., Ivette, d. H.L., Rodrigues, L.H.: Tail index estimation for heavy-tailed models: accommodation of bias in weighted log-excesses. J. R. Stat. Soc. Ser. B 70(Part 1), 31–52 (2008)
Grintsyavichyus, A.: On a random difference equation. Lith. Math. J. 21(4), 302–305 (1981)
Guivarc’h, Y.: Sur une extension de la notion de loi semi-stable. Ann. Inst. Henri Poincaré B Calc. Probab. Stat. 26(2), 261–285 (1990)
Guivarc’h, Y.: Heavy tail properties of stationary solutions of multidimensional stochastic recursions. In: IMS Lecture Notes Monogr. Ser., vol. 48, pp. 85–99. Institute of Mathematical Statistics, Beachwood (2006)
Kahane, J.-P., Peyrière, J.: Sur certaines martingales de Benoit Mandelbrot. Adv. Math. 22(2), 131–145 (1976)
Kesten, H.: Random difference equations and renewal theory for products of random matrices. Acta Math. 131, 207–248 (1973)
Klüppelberg, C., Pergamenchtchikov, S.: The tail of the stationary distribution of a random coefficient AR(q) model. Ann. Appl. Probab. 14(2), 971–1005 (2004)
Liu, Q.: On generalized multiplicative cascades. Stoch. Process. Appl. 86(2), 263–286 (2000)
Mandelbort, B.: Intermittent turbulence in self-similar cascades: divergence of high moments and dimension of the carrier. J. Fluid Mech. 62(2), 331–358 (1974)
Ossiander, M., Waymire, E.C.: Statistical estimation for multiplicative cascades. Ann. Stat. 28(6), 1533–1560 (2000)
Peng, L.: Asymptotically unbiased estimators for the extreme-value index. Stat. Probab. Lett. 38(2), 107–115 (1998)
Resnick, S.I.: Heavy tail modeling and teletraffic data. Ann. Stat. 25(5), 1805–1869 (1997) (with discussion and a rejoinder by the author)
Stelzer, R.: On Markov-switching ARMA processes—stationarity, existence of moments and geometric ergodicity. Econom. Theory 25, 43–62 (2009)
Author information
Authors and Affiliations
Corresponding author
Additional information
The second author is supported in part by the NSF grant DMS-0505628.
Rights and permissions
About this article
Cite this article
Baek, C., Pipiras, V., Wendt, H. et al. Second order properties of distribution tails and estimation of tail exponents in random difference equations. Extremes 12, 361–400 (2009). https://doi.org/10.1007/s10687-009-0082-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10687-009-0082-x
Keywords
- Random difference equations
- Tail exponent and its estimation
- Second order regular variation
- ARCH models
- Multiplicative cascades