Abstract.
The GARCH algorithm is the most renowned generalisation of Engle's original proposal for modelising returns, the ARCH process. Both cases are characterised by presenting a time dependent and correlated variance or volatility. Besides a memory parameter, b, (present in ARCH) and an independent and identically distributed noise, ω, GARCH involves another parameter, c, such that, for c=0, the standard ARCH process is reproduced. In this manuscript we use a generalised noise following a distribution characterised by an index qn, such that qn=1 recovers the Gaussian distribution. Matching low statistical moments of GARCH distribution for returns with a q-Gaussian distribution obtained through maximising the entropy \(S_{q}=\frac{1-\sum_{i}p_{i}^{q}}{q-1}\), basis of nonextensive statistical mechanics, we obtain a sole analytical connection between q and \(\left( b,c,q_{n}\right) \) which turns out to be remarkably good when compared with computational simulations. With this result we also derive an analytical approximation for the stationary distribution for the (squared) volatility. Using a generalised Kullback-Leibler relative entropy form based on Sq, we also analyse the degree of dependence between successive returns, zt and zt+1, of GARCH(1,1) processes. This degree of dependence is quantified by an entropic index, qop. Our analysis points the existence of a unique relation between the three entropic indexes qop, q and qn of the problem, independent of the value of (b,c).
Similar content being viewed by others
References
S. Abe, N. Suzuki, Europhys. Lett. 65, 581 (2004)
M. Ausloos, K. Ivanova, Phys. Rev. E 63, 047201 (2001)
O.A. Rosso, M.T. Martin, A. Plastino, Physica A 320, 497 (2003)
R. Osorio, L. Borland, C. Tsallis, in Nonextensive Entropy - Interdisciplinary Applications, edited by M. Gell-Mann, C. Tsallis (Oxford University Press, New York, 2004)
S.M. Duarte Queirós, Physica A 344, 279 (2004)
J.P. Bouchaud, M. Potters, Theory of Financial Risks: From Statistical Physics to Risk Management (Cambridge University Press, Cambridge, 2000); R.N. Mantegna, H.E. Stanley: An introduction to Econopysics: Correlations, Complexity in Finance (Cambridge University Press, Cambrigde, 1999)
R.F. Engle, Econometrica 50, 987 (2002)
F. Black, M. Scholes, J. Political Economy 81, 637 (1973)
T. Bollerslev, R.Y. Chou, K.F. Kroner, J. Econometrics 52, 5 (1992)
S.H. Poon, C.W.J. Granger, J. Econ. Lit. 41, 478 (2003)
T. Bollerslev. J. Econometrics 31, 307 (1986); S.J. Taylor, Modelling Financial Time Series (Wiley, New York, 1986)
F. Baldovin, Physica A, 342, 119 (2004)
S.M. Duarte Queirós, C. Tsallis, Europhys. Lett. 69, (2005)
U. Frisch, Turbulence: The Legacy of A. Kolmogorov, (Cambrigde University Press, Cambridge, 1997)
Z. Ding, C.W.J. Granger, R.F. Engle, J. Emp. Fin. 1, 83 (1993)
The condition b1+c1<1 guarantees this property for any GARCH(r,s) process boller, hansen
B.E. Hansen, Econ. Lett. 36, 181 (1991)
C. Beck, E.G. Cohen, Physica A 322, 267 (2003)
P. Embrechts, C. Kluppelberg, T. Mikosch, Modelling Extremal Events for Insurance and Finance, Applications of Mathematics (Springer-Verlag, Berlin, 1997)
C. Tsallis, J. Stat. Phys. 52 , 479 (1988). A regularly an updated bibliograhy on the subject is avaible at http://tsallis.cat.cbpf.br/biblio.htm
For systems presenting equiprobability whose (allowed) phase space, Ω, grows like Ω∼Nρ \(\left( \rho >0\right) \), if we consider \(q=1-\frac{1}{\rho }\), Sq will be proportional to N (and so extensive) in the same way SBG is for systems with Ω∼μN \(\left( \mu >1\right) ,\) respecting Clausius concept on macroscopic entropy and thermodynamics. In a probability context this can be related with an amendment in the law of probability of a system composed of N independent parts. A sheer analysis on this question can be found in references tsallis-erice, sato-tsallis
C. Tsallis, Proceedings of the 31st Workshop of the International School of Solid State Physics “Complexity, Metastability and Nonextensivity", held at the Ettore Majorana Foundation and Centre for Scientific Culture (Erice, July 2004), edited by C. Beck, A. Rapisarda, G. Benedeck, C. Tsallis (World Scientific, Singapore, 2005), e-print arXiv:cond-mat/0409631
Y. Sato, C. Tsallis, Proceedings of the Summer School and Conference on Complexity (Patras and Olympia, July 2004), edited by T. Bountis, International Journal of Bifurcation and Chaos (2005), e-print arXiv:cond-mat/0411073
C. Tsallis, M. Gell-Mann, Y. Sato, Proc. Natl. Acad. Sci. USA 102, 15377 (2005)
M.L. Lyra, C. Tsallis, Phys. Rev. Lett. 80, 53 (1998); F. Baldovin, A. Robledo, Europhys. Lett. 60, 518 (2000)
L. Borland, Phys. Rev. E 57, 6634 (1998)
C. Beck, G.S. Lewis, H.L. Swinney, Phys. Rev. E 63, R035303 (2001)
With a little algebra it is possible to verify that the GARCH(1,1) represents an autoregressive moving average (ARMA) process in zt2 boller
G. Wilk, Z. Włodarczyk, Phys. Rev. Lett. 84, 2770 (2000)
C. Beck, Phys. Rev. Lett 87, 180601 (2001)
V. Latora, A. Rapisarda, C. Tsallis, Phys. Rev. E 64, 056134 (2001)
Nonextensive Entropy - Interdisciplinary Applications, edited by M. Gell-Mann, C. Tsallis, (Oxford University Press, New York, 2004)
C. Tsallis, A.R. Plastino, R.S. Mendes, Physica A 261, 534 (1998)
D. Prato, C. Tsallis, Phys. Rev. E 60, 2398 (1999)
C. Tsallis, Braz. J. Phys 29, 1 (1999)
A.M.C. de Souza, C. Tsallis, Physica A 236, 52 (1997)
L. Borland, Phys. Rev. Lett. 89, 098701 (2002); L. Borland, Quantitative Finance 2, 415 (2002)
J.P. Fouque, G. Papanicolaou, K.R. Sircar, Derivatives in Financial Markets with Stochastic Volatility (Cambridge University Press, Cambridge, 2000)
T.G. Andersen, T. Bollerslev, J. Finance 52, 975 (1997)
P. Willmott, On Quantitative Finance, 2nd edn. (John Wiley & Sons, New York, 2000)
L. Borland, J.P. Bouchaud, e-print arXiv:cond-mat/0403022
Since σt and ωt are uncorrelated and independent, for a given value σ, we can do a change of variable, equation (1), which transforms equation (16) into the conditional probability equation (25)
C. Tsallis, Phys. Rev. E 58, 1442 (1998)
S. Kullback, R.A. Leibler, Ann. Math. Stat. 22, 79 (1961)
Optimal in the sense that its two extreme values correspond to full independence/dependence borland-plastino-tsallis.
L. Borland, A.R. Plastino, C. Tsallis, J. Math. Phys. 39, 6490 (1998) [Erratum: J. Math. Phys. 40, 2196 (1999)]
C. Tsallis, Physica A 340, 1 (2004)
S.M. Duarte Queirós, Quantitative Finance 5, 475 (2005)
F.C. Drost, T.E. Nijman, Econometrica 61, 909 (1993)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Queirós, S., Tsallis, C. On the connection between financial processes with stochastic volatility and nonextensive statistical mechanics. Eur. Phys. J. B 48, 139–148 (2005). https://doi.org/10.1140/epjb/e2005-00366-1
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1140/epjb/e2005-00366-1