Automatic Autocorrelation and Spectral Analysis
If different people estimate spectra from the same finite number of stationary stochastic observations, their results will generally not be the same. The reason is that several subjective decisions or choices have to be made during the current practice of spectral analysis, which influence the fi...
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
Springer
2012
|
| Subjects: | |
| Online Access: | https://scholar.dlu.edu.vn/thuvienso/handle/DLU123456789/30540 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institutions: | Thư viện Trường Đại học Đà Lạt |
|---|
| Summary: | If different people estimate spectra from the same finite number of stationary
stochastic observations, their results will generally not be the same. The reason is
that several subjective decisions or choices have to be made during the current
practice of spectral analysis, which influence the final spectral estimate. This
applies also to the analysis of unique historical data about the atmosphere and the
climate. That might be one of the reasons that the debate about possible climate
changes becomes confused. The contribution of statistical signal processing can be
that the same stationary statistical data will give the same spectral estimates for
everybody who analyses those data. That unique solution will be acceptable only if
it is close to the best attainable accuracy for most types of stationary data. The
purpose of this book is to describe an automatic spectral analysis method that
fulfills that requirement. It goes without saying that the best spectral description
and the best autocorrelation description are strongly related because the Fourier
transform connects them.
Three different target groups can be distinguished for this book. |
|---|