Wavelet-based Estimation of Generalized Fractional Process

Summary

Objectives : This paper aims to propose an estimation procedure for the parameters of a generalized fractional process, a fairly general model of long-memory applicable in modeling biomedical signals whose autocorrelations exhibit hyperbolic decay.

Methods : We derive a wavelet-based weighted least squares estimator of the long-memory parameter based on the maximal-overlap estimator of the wavelet variance. Short-memory parameters can then be estimated using standard methods. We illustrate our approach by an example applying ECG heart rate data.

Results and Conclusion : The proposed method is relatively computationally and statistically efficient. It allows for estimation of the long-memory parameter without knowledge of the short-memory parameters. Moreover it provides a more general model of biomedical signals that exhibit periodic long-range dependence, such as ECG data, whose relatively unobtrusive recording may be advantageous in assessing or predicting some physiological or pathological conditions from the estimated values of the parameters.

Keywords

Wavelet coefficients - long-memory - generalized fractional process

• References

• 1. Bullmore E. et al. Wavelets and statistical analysis of functional magnetic resonance images of the human brain. Statistical Methods in Medical Research 2003; 12: 375-399.
• 2. Beran J, Bhansali RJ, Ocker D. On unified model selection for stationary and nonstationary short- and long-memory autoregressive processes. Biometrika 1998; 85 (04) 921-934.
• 3. Nakamura Y, Yamamoto Y, Muraoka I. Autonomic control of heart rate during physical exercise and fractional dimension of heart rate variability. Journal of Applied Physiology 1993; 74: 875-881.
• 4. Bigger JT. et al. Power law behavior of RR-interval variability in healthy middle-aged persons, patients with recent acute myocardial infarction, and patients with heart transplants. Circulation 1996; 93: 2142-2151.
• 5. Brockwell P, Davis R. Time Series: Theory and Methods. New York: Springer-Verlag; 1991
• 6. Nason G, Sapatinas T, Sawczenko A. Wavelet packet modeling of infant sleep state using heart rate data. Sankhya Series B 2001; 63: 199-217.
• 7. Gray HL, Zhang NF, Woodward W. On Generalized Fractional Processes. Journal of Time Series Analysis 1989; 10 (03) 233-257.
• 8. Ramachandran R, Bhethanabotla VN. Generalized Autoregressive Moving Average Modeling of the Bellcore Data. Proceedings of the 25th Annual IEEE Conference on Local Computer Networks. Tampa, Florida, USA: IEEE Computer Society Press, 2000: 654-661.
• 9. Chung C. Estimating a generalized long-memory process. Journal of Econometrics 1996; 73: 237-259.
• 10. Whitcher B. Wavelet-based estimation for seasonal long-memory. Technometrics 2004; 46 (02) 225-238.
• 11. Walden A. Wavelet Analysis of Discrete Time Series. Proceedings of the European Congress of Mathematics. Barcelona: Birkhauser; 2000
• 12. Fan Y. On the Approximate Decorrelation Property of Discrete Wavelet Transform for Fractionally Differenced Process. IEEE Transactions on Information Theory 2003; 49: 516-521.
• 13. Percival D. On Estimation of the Wavelet Variance. Biometrika 1995; 82 (03) 619-631.
• 14. Bickel P, Doksum K. Mathematical Statistics. San Francisco: Holden-Day, Inc.; 1977
• 15. Moody G, Goldberger A. Heart rate time series. Available from URL: http://ecg.mit.edu/time-series