Activity Number:
|
238
|
Type:
|
Invited
|
Date/Time:
|
Tuesday, August 13, 2002 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Business & Economics Statistics Section*
|
Abstract - #300270 |
Title:
|
Wavelet-Based Estimation for Seasonal Long-Memory Processes
|
Author(s):
|
Brandon Whitcher*+
|
Affiliation(s):
|
National Center for Atmospheric Research
|
Address:
|
P.O. Box 3000, Boulder, Colorado, 80307-3000,
|
Keywords:
|
discrete wavelet packet transform ; Gegenbauer process ; maximum likelihood estimation ; time series
|
Abstract:
|
We introduce the multiscale analysis of seasonal persistent processes; i.e., time series models with a singularity in their spectral density function at one or more frequencies in [0,1/2]. The discrete wavelet packet transform (DWPT) is introduced as an alternative method to spectral techniques for analyzing time series that exhibit seasonal long-memory. Approximate maximum likelihood estimation is performed by replacing the variance/covariance matrix with a diagonalized matrix based on the DWPT. From simulation studies, maximum likelihood estimation is found to be quite robust when using either the true spectral density function or the log-linear approximation. Applications of this methodology to atmospheric CO2 measurements and U.S. quarterly tourism revenue are presented.
|