A New Class of Tail-dependent Time-Series Models and Its Applications in Financial Time Series

In this paper, the gamma test is used to determine the order of lag-k tail dependence existing in financial time series. Using standardized return series, statistical evidences based on the test results show that jumps in returns are not transient. New time series models which combine a specific class of max-stable processes, Markov processes, and GARCH processes are proposed and used to model tail dependencies within asset returns. Estimators for parameters in the models are developed and proved to be consistent and asymptotically joint normal. These new models are tested on simulation examples and some real data, the S&P 500.

[1]  Qiwei Yao,et al.  Inference in ARCH and GARCH models with heavy-tailed errors , 2003 .

[2]  J. Doob.  Stochastic processes , 1953 .

[3]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[4]  R. Engle.  Dynamic Conditional Correlation , 2002 .

[5]  李幼升,et al.  Ph , 1989 .

[6]  Nicholas G. Polson,et al.  The Impact of Jumps in Volatility and Returns , 2000 .

[7]  P. Hall,et al.  Moving-maximum models for extrema of time series , 2002 .

[8]  R. Lund.  Estimation in Conditionally Heteroscedastic Time Series Models , 2006 .

[9]  Sidney I. Resnick,et al.  Basic properties and prediction of max-ARMA processes , 1989, Advances in Applied Probability.

[10]  T. Bollerslev,et al.  Generalized autoregressive conditional heteroskedasticity , 1986 .

[11]  R. Engle.  Dynamic Conditional Correlation : A Simple Class of Multivariate GARCH Models , 2000 .

[12]  H. Akaike.  A new look at the statistical model identification , 1974 .

[13]  S. Nandagopalan.  ON THE MULTIVARIATE EXTREMAL INDEX , 1994 .

[14]  Jon Danielsson,et al.  The emperor has no clothes: Limits to risk modelling , 2000 .

[15]  P. Ritchken,et al.  Option Valuation with Jumps in Returns and Volatility , 2002 .

[16]  L. de Haan,et al.  A Spectral Representation for Max-stable Processes , 1984 .

[17]  J. Corcoran.  Modelling Extremal Events for Insurance and Finance , 2002 .

[18]  Sidney I. Resnick,et al.  Prediction of Stationary Max-Stable Processes , 1993 .

[19]  P. Embrechts,et al.  Risk Management: Correlation and Dependence in Risk Management: Properties and Pitfalls , 2002 .

[20]  Zhengjun Zhang,et al.  The estimation of M4 processes with geometric moving patterns , 2008 .

[21]  Zhengjun Zhang,et al.  Quotient correlation: A sample based alternative to Pearson’s correlation , 2008, 0804.1001.

[22]  Paul Deheuvels,et al.  Point processes and multivariate extreme values , 1983 .

[23]  S. Resnick,et al.  Limit theory for multivariate sample extremes , 1977 .

[24]  Patrick Billingsley,et al.  Statistical inference for Markov processes , 1961 .

[25]  M. R. Leadbetter,et al.  Extremes and Related Properties of Random Sequences and Processes: Springer Series in Statistics , 1983 .

[26]  T. Mikosch,et al.  Limit theory for the sample autocorrelations and extremes of a GARCH (1,1) process , 2000 .

[27]  Thomas Mikosch,et al.  Whittle estimation in a heavy-tailed GARCH(1,1) model , 2002 .

[28]  D. Straumann.  Estimation in Conditionally Herteroscedastic Time Series Models , 2004 .

[29]  Thorsten Rheinländer.  Risk Management: Value at Risk and Beyond , 2003 .

[30]  A. McNeil,et al.  Estimation of tail-related risk measures for heteroscedastic financial time series: an extreme value approach , 2000 .

[31]  P. Billingsley,et al.  Statistical Methods in Markov Chains , 1961 .

[32]  R. Smith.  Statistics of Extremes, with Applications in Environment, Insurance, and Finance , 2003 .

[33]  J. Pickands.  Statistical Inference Using Extreme Order Statistics , 1975 .

[34]  Richard L. Smith,et al.  Characterization and Estimation of the Multivariate Extremal Index , 1996 .

[35]  S. Resnick.  Extreme Values, Regular Variation, and Point Processes , 1987 .

[36]  Richard L. Smith,et al.  The behavior of multivariate maxima of moving maxima processes , 2004 .

[37]  Masaaki Sibuya,et al.  Bivariate extreme statistics, I , 1960 .