Introduction

A time series is a sequence of data points obtained over successive uniform time

intervals. The word “time” can also be interpreted loosely to mean a time-like

variable that provides the ordering and spacing for the data points. In this book,

we are mainly interested in a particular type of time series, known as time series

with mixed spectra, which can be expressed as a sum of sinusoids plus random

noise. Time series of this type are abundant in a variety of science and engi-

neering applications, including astronomy, biology, econometrics, geophysics,

meteorology, rotating machinery, radar, sonar, and telecommunications. A main

objective for spectral analysis of such time series is to detect and estimate the

hidden periodicities represented by the sinusoidal functions.