| Analysis of Long Memory Processes Due to Time Varying Frequency |
| For non-stationary processes with frequencies varying over time, traditional Fourier spectral analysis has disadvantages in characterizing and predicting their behavior. Wavelet analysis had been applied as powerful methodology to investigate such data in diverse fields such as signal processing and medical imaging. New methodology referred as EARMA is able to explain certain types of non-stationary processes for which traditional Fourier analysis, wavelet approaches or piecewise methods fail. This paper introduces the new method and shows its basic properties. In addition, a comparison study with other existing methods is performed through simulated and real data. |
|
Eunha Choi Southern Methodist University Student Poster Session |
 |
 |
April 4-5, 2003
Texas A&M University
College Station, TX
Email:
cots@stat.tamu.edu
Fax: (979) 845-3144
Phone: (979) 845-3141