Nonparametric Autoregression with Multiplicative Volatility and Additive mean

For over a decade, nonparametric modelling has been successfully applied to study nonlinear structures in financial time series. It is well known that the usual nonparametric models often have less than satisfactory performance when dealing with more than one lag. When the mean has an additive structure, however, better estimation methods are available which fully exploit such a structure. Although in the past such nonparametric applications had been focused more on the estimation of the conditional mean, it is equally if not more important to measure the future risk of the series along with the mean. For the volatility function, i.e., the conditional variance given the past, a multiplicative structure is more appropriate than an additive one, as the volatility is a positive scale function and a multiplicative model provides a better interpretation of each lagged value's influence on such a function. In this paper we consider the joint estimation of both the additive mean and the multiplicative volatility. The technique used is marginally integrated local polynomial estimation. The procedure is applied to the DEM/USD (Deutsche Mark/US Dollar) daily exchange returns.

[1]  T. Nijman,et al.  Temporal Aggregation of GARCH Processes. , 1993 .

[2]  Stephen Gray,et al.  Semiparametric ARCH models , 2001 .

[3]  W. Härdle,et al.  Foreign Exchange Rates Have Surprising Volatility , 1996 .

[4]  H. Tong,et al.  ON ESTIMATING THRESHOLDS IN AUTOREGRESSIVE MODELS , 1986 .

[5]  Jianqing Fan,et al.  Local polynomial modelling and its applications , 1994 .

[6]  R. Tweedie.  Sufficient conditions for ergodicity and recurrence of Markov chains on a general state space , 1975 .

[7]  Wolfgang Karl Härdle,et al.  Local polynomial estimators of the volatility function in nonparametric autoregression , 1997 .

[8]  D. Tjøstheim,et al.  Functional Identification in Nonlinear Time Series , 1991 .

[9]  C. J. Stone,et al.  Optimal Global Rates of Convergence for Nonparametric Regression , 1982 .

[10]  E. Nummelin,et al.  Geometric ergodicity of Harris recurrent Marcov chains with applications to renewal theory , 1982 .

[11]  P. Robinson.  Robust Nonparametric Autoregression , 1984 .

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

[13]  Wolfgang Härdle,et al.  Nonparametric Time Series Analysis, a selectiv review with examples , 1995 .

[14]  Ruey S. Tsay,et al.  Nonlinear Additive ARX Models , 1993 .

[15]  J. Hinde.  XploRe: An Interactive Statistical Computing Environment , 1997 .

[16]  Alexander B. Tsybakov.  Robust reconstruction of functions by the local approximation method , 1986 .

[17]  Stefan Sperlich,et al.  Estimation of Derivatives for Additive Separable Models , 1999 .

[18]  Wolfgang Härdle,et al.  XploRe: An Interactive Statistical Computing Environment , 1995 .

[19]  Hung Man Tong,et al.  Threshold models in non-linear time series analysis. Lecture notes in statistics, No.21 , 1983 .

[20]  Tail Behaviour of the Stationary Density of General Non-Linear Autoregressive Processes of Order One , 1993 .

[21]  T. Ozaki,et al.  Modelling nonlinear random vibrations using an amplitude-dependent autoregressive time series model , 1981 .

[22]  Paul Waltman,et al.  A Threshold Model , 1974 .

[23]  R. Meese,et al.  An Empirical Assessment of Non-Linearities in Models of Exchange Rate Determination , 1991 .

[24]  Matthew P. Wand,et al.  Kernel Smoothing , 1995 .

[25]  Dag Tjøstheim,et al.  Additive Nonlinear ARX Time Series and Projection Estimates , 1997, Econometric Theory.

[26]  Holger Rootzén,et al.  On the functional central limit theorem for martingales , 1977 .

[27]  S. H. Hsieh,et al.  THRESHOLD MODELS FOR NONLINEAR TIME SERIES ANALYSIS. , 1987 .

[28]  W. Härdle,et al.  Estimation of additive regression models with known links , 1996 .

[29]  Y. Davydov.  Mixing Conditions for Markov Chains , 1974 .

[30]  Lijian Yang,et al.  Nonparametric Lag Selection for Time Series , 2000 .

[31]  O. Linton,et al.  A kernel method of estimating structured nonparametric regression based on marginal integration , 1995 .

[32]  Dag Tjøstheim,et al.  Nonparametric Identification of Nonlinear Time Series: Projections , 1994 .

[33]  R. Engle,et al.  Semiparametric ARCH Models , 1991 .

[34]  C. Gouriéroux,et al.  Qualitative threshold arch models , 1992 .

[35]  H. Rootzén.  On the functional central limit theorem for martingales, II , 1977 .

[36]  P. Robinson.  NONPARAMETRIC ESTIMATORS FOR TIME SERIES , 1983 .

[37]  M. Wand,et al.  Multivariate Locally Weighted Least Squares Regression , 1994 .

[38]  C. J. Stone,et al.  Consistent Nonparametric Regression , 1977 .

[39]  Wolfgang Karl Härdle,et al.  Nonparametric Vector Autoregression , 1998 .

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