ABSTRACT

In this section, the spectral analysis method is introduced as a basic tool

for stationary time series analysis. By means of spectral analysis, we

can capture the characteristics of time series by decomposing time se-

ries into trigonometric functions at each frequency and by representing

the features with the strength of each periodic component. The subjects

discussed here will lead to the definition of the power spectrum and the

periodogram of time series, computational methods, variance reduction

and smoothingmethods.Moreover, an efficient method of computing pe-

riodograms is presented using fast Fourier transforms (FFT). The readers

interested in the spectral analysis of time series are referred to Brillinger

(1974), Bloomfied (1976), Akaike and Nakagawa (1989) and Brockwell

and Davis (1991).