Bayesian Nonparametric Adaptive Spectral Density Estimation for Financial Time Series

Discrimination between non-stationarity and long-range dependency is a difficult and long-standing issue in modelling financial time series. This paper uses an adaptive spectral technique which jointly models the non-stationarity and dependency of financial time series in a non-parametric fashion assuming that the time series consists of a finite, but unknown number, of locally stationary processes, the locations of which are also unknown. The model allows a non-parametric estimate of the dependency structure by modelling the auto-covariance function in the spectral domain. All our estimates are made within a Bayesian framework where we use aReversible Jump Markov Chain Monte Carlo algorithm for inference. We study the frequentist properties of our estimates via a simulation study, and present a novel way of generating time series data from a nonparametric spectrum. Results indicate that our techniques perform well across a range of data generating processes. We apply our method to a number of real examples and our results indicate that several financial time series exhibit both long-range dependency and non-stationarity.

[1]  S. Satchell,et al.  GARCH model with cross-sectional volatility: GARCHX models , 2005 .

[2]  D. Brillinger.  Time series - data analysis and theory , 1981, Classics in applied mathematics.

[3]  Francis X. Diebold,et al.  Modeling and Forecasting Realized Volatility , 2001 .

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

[5]  R. Dahlhaus.  Fitting time series models to nonstationary processes , 1997 .

[6]  David S. Stoffer,et al.  Local Spectral Analysis via a Bayesian Mixture of Smoothing Splines , 2009 .

[7]  Andrew W. Lo,et al.  Spectral analysis of stock-return volatility, correlation, and beta , 2015, 2015 IEEE Signal Processing and Signal Processing Education Workshop (SP/SPE).

[8]  Adaptive Spectral Estimation for Nonstationary Time Series , 2014 .

[9]  Sally Wood,et al.  Bayesian mixture of splines for spatially adaptive nonparametric regression , 2002 .

[10]  J. Zakoian.  Threshold heteroskedastic models , 1994 .

[11]  P. Hansen,et al.  Realized GARCH: A Joint Model of Returns and Realized Measures of Volatility , 2010 .

[12]  David R. Brillinger,et al.  Time Series: Data Analysis and Theory. , 1982 .

[13]  Stephen Gray.  Modeling the Conditional Distribution of Interest Rates as a Regime-Switching Process , 1996 .

[14]  P. Manimaran,et al.  Modelling Financial Time Series , 2006 .

[15]  P. Whittle.  Curve and Periodogram Smoothing , 1957 .

[16]  James D. Hamilton,et al.  Autoregressive conditional heteroskedasticity and changes in regime , 1994 .

[17]  David Ardia,et al.  Markov-Switching GARCH Models in R: The MSGARCH Package , 2016, Journal of Statistical Software.

[18]  G. Wahba.  Spline models for observational data , 1990 .

[19]  Mike K. P. So,et al.  A Stochastic Volatility Model With Markov Switching , 1998 .

[20]  Daniel B. Nelson.  CONDITIONAL HETEROSKEDASTICITY IN ASSET RETURNS: A NEW APPROACH , 1991 .

[21]  R. Engle.  Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation , 1982 .

[22]  B. Mandlebrot.  The Variation of Certain Speculative Prices , 1963 .

[23]  Sally Wood,et al.  AdaptSPEC: Adaptive Spectral Estimation for Nonstationary Time Series , 2012 .

[24]  T. Bollerslev,et al.  A CONDITIONALLY HETEROSKEDASTIC TIME SERIES MODEL FOR SPECULATIVE PRICES AND RATES OF RETURN , 1987 .

[25]  Kin Lam,et al.  A threshold stochastic volatility model , 2002 .

[26]  Jun Cai.  A Markov Model of Switching-Regime ARCH , 1994 .

[27]  L. Glosten,et al.  On the Relation between the Expected Value and the Volatility of the Nominal Excess Return on Stocks , 1993 .

[28]  Marc S. Paolella,et al.  Mixed Normal Conditional Heteroskedasticity , 2004 .

[29]  Stephen L Taylor,et al.  Modelling Financial Time Series , 1987 .

[30]  S. Taylor.  Financial Returns Modelled by the Product of Two Stochastic Processes , 1961 .

[31]  Luc Bauwens,et al.  A Bayesian method of change-point estimation with recurrent regimes: Application to GARCH models , 2014 .