Handbook of Statistics 3: Time Series in the Frequency Domain

P. R. Krishnaiah0444867260, 9780444867261

Hardbound. This volume of the Handbook is concerned particularly with the frequency side, or spectrum, approach to time series analysis. This approach involves essential use of sinusoids and bands of (angular) frequency, with Fourier transforms playing an important role. A principal activity is thinking of systems, their inputs, outputs, and behavior in sinusoidal terms. In many cases, the frequency side approach turns out to be simpler with respect to computational, mathematical, and statistical aspects. In the frequency approach, an assumption of stationarity is commonly made. However, the essential roles played by the techniques of complex demodulation and seasonal adjustment show that stationarity is far from being a necessary condition. Assumptions of Gaussianity and linearity are also commonly made and yet, as a variety of the papers illustrate, these assumptions are not necessary. This volume complements Handbook of Statistics 5: Time Series in the

---

Table of contents :
Handbook ststistics 3: Time Series in the Frequency Domain……Page 1
Table of contents……Page 3
Preface……Page 9
Contributors……Page 10
1. Wiener Filtering……Page 12
2. The Finite Fourier Transform of a Stationary Process……Page 31
3. Seasonal and Calendar Adjustment……Page 48
4. Optimal Inference in the Frequency Domain……Page 82
5. Applications of Spectral Analysis in Econometrics……Page 102
6. Signal Estimation……Page 119
7. Complex Demodulation: Some Theory and Applications……Page 132
8. Estimating the Gain of A Linear Filter from Noisy Data……Page 164
9. A Spectral Analysis Primer……Page 175
10. Robust-Resistant Spectral Analysis……Page 190
11. Autoregressive Spectral Estimation……Page 225
12. Threshold Autoregression and Some Frequency-Domain Characteristics……Page 252
13. The Frequency-Domain Approach to the Analysis of Closed-Loop Systems……Page 277
14. The Bispectral Analysis of Nonlinear Stationary Time Series with Reference to Bilinear Time-Series Models……Page 294
15. Frequency-Domain Analysis of Multidimensional Time-Series Data……Page 321
16. Review of Various Approaches to Power Spectrum Estimation……Page 343
17. Cumulants and Cumulant Spectra……Page 369
18. Replicated Time-Series Regression: An Approach to Signal Estimation and Detection……Page 383
19. Computer Programming of Spectrum Estimation……Page 409
20. Likelihood Ratio Tests on Covariance Matrices and Mean Vectors of Complex Multivariate Normal Populations and Their Applications in Time Series……Page 438
Subject Index……Page 476
Handbook of Statistics: Contents of Previous Volumes……Page 482