Abstract
The spectral density of a discrete-time wide-sense stationary, real Gaussian random process from a set of 2N observations can be estimated by suitable processing of the empirical spectral density estimates that require a certain bandwidth. This is indicative that an appropriate bandwidth must be chosen in order to derive desired estimates. Wavelet techniques are seen to be promising for such application. The work presented here aims to present an estimation technique (wavelet) based on these paradigms; a) large-sample model for the data, b) inference on the wavelet coefficients of the log spectral density. This technique is demonstrated through examples. The results show the automatic adjustment of the bandwidth to the data as well as the different resolution/noise tradeoffs that may be obtained.
| Original language | English (US) |
|---|---|
| State | Published - 1994 |
| Externally published | Yes |
| Event | Proceedings of the 1994 IEEE International Symposium on Information Theory - Trodheim, Norw Duration: Jun 27 1994 → Jul 1 1994 |
Other
| Other | Proceedings of the 1994 IEEE International Symposium on Information Theory |
|---|---|
| City | Trodheim, Norw |
| Period | 6/27/94 → 7/1/94 |
ASJC Scopus subject areas
- Theoretical Computer Science
- Information Systems
- Modeling and Simulation
- Applied Mathematics