Frequency-Domain Estimation of Continuous-Time Bilinear Processes

Abstract

In this paper, we study in frequency domain some probabilistic and statistical properties of continuous-time version of the well-known bilinear processes driven by a standard Brownian motion. This class of processes which encompasses many commonly used processes in the literature was defined as a nonlinear stochastic differential equation which has raised considerable interest in the last few years. So, the ${\mathbb {L}}_{2}$-structure of the process is studied and its covariance function is given. These structures will lead to study the strong consistency and asymptotic normality of the Whittle estimates of the unknown parameters involved in the process. Finite sample properties are also considered through Monte Carlo experiments. In end, the model is then used to model the exchanges rate of the Algerian Dinar against the US dollar.

Keywords

Continuous-time bilinear processes / Whittle estimator / Consistency / Asymptotic normality

References

[1] Bernt Ø. Stochastic Differential Equations: An Introduction with Applications. 2000 New York: Springer

[2] Bibi A, Merahi F. A note on ${\mathbb{L}}_{2} $-structure of continuous-time bilinear processes with time-varying coefficients. Int. J. Stat. Prob.. 2015, 4 3 150-160

[3] Brillinger DR. Time Series: Data Analysis and Theory. 1975 New York: Holt, Reinhart

[4] Brockwell PJ. Continuous-Time ARMA Processes. Handbook of Statistics. 2001 Amsterdam: North Holland. 249-276

[5] Dzhaparidze KO, Yagloma AM. Spectrum Parameter Estimation in Time Series Analysis. Developments in Statistics, Ch. 1. 1983 New York: Academic Press. 1-96

[6] Florens-Zmirou D. Approximate discrete time schemes for statistics of diffusion processes. Statistics. 1989, 20 547-557

[7] Granger CWJ, Andersen AP. An introduction to bilinear time series models. 1978 Gottingen: Vandenhoeck and Rpurecht

[8] Hannan EJ. The asymptotic theory of linear time series models. J. Appl. Probab.. 1973, 10 130-145

[9] Kelley WG, Peterson AC. The Theory of Differential Equations. 2010 New York: Springer

[10] Klüppelberg C, Lindner A, Maller R. A continuous time GARCH process driven by a Lévy process: Stationarity and second order behaviour. J. Appl. Probab.. 2004, 41 601-622

[11] Kutoyants YA. Statistical Inference for Ergodic Diffusion Processes. 2004 London: Springer

[12] Le Breton A, Musiela M. A study of one-dimensional bilinear differential model for stochastic processes. Probab. Math. Stat.. 1984, 4 1 91-107

[13] Major P. Multiple Wiener-Itô Integrals. Lecture Notes in Mathematics. 1981 New York: Springer. 849

[14] Subba Rao T, Terdik G. On the theory of discrete and continuous bilinear time series models. Handb. Stat.. 2003, 21 827-870

[15] Wegman EJ, Schwartz SC, Thomas JB. Topics in Non-Gaussian Signal Processing. 1989 New York: Springer