This book is an up-to-date introduction to univariate spectral analysis aimed at graduate students, which reflects a new scientific awareness of spectral complexity, as well as the widespread use of spectral analysis on digital computers with considerable computational power. The text provides theoretical and computational guidance on the available techniques, emphasizing those that work in practice. It gives equal weight to both algorithms and statistical theory and is valuable for the many examples it gives showing the application of spectral analysis to real data sets. The book is unique in placing special emphasis on the multitaper technique, which can successfully handle spectra with intricate structure and data with or without spectral lines. The text contains a large number of exercises.
"...this is a beautifully crafted book, which can be read at several levels. The beginner can concentrate on principles, study the algorithms and the numerical examples, and then begin to use the Common USP code obtainable through electronic-mail. The experienced reader can proceed to study the more advanced material that the authors have isolated in 'Comments and Extensions' to appropriate sections presenting more general material. This presentation style works very well indeed, because it has enabled the authors to produce a volume that is both elementary and advanced...This is an outstanding volume, one that ought to be on the bookshelves of students as well as those of experienced practitioners of this arcane art." Sven Treitel, American Scientist "...provides a very thorough and modern introduction to spectral analysis of univariate time series with an emphasis on the multitaper method. This book would serve well as a textbook for an introduction to spectral analysis for advanced undergraduate or graduate students, even without mentioning multitaper methods. I also recommend it as a reference book for anyone interested in the field, and it certainly belongs in a university library." Dennis D. Cox, Technometrics "This is a great book for any one who uses or wants to learn to use spectral analysis...The authors take an applied approach, not a watered down approach...the suthors supply the reader with ample references to the more theoretical details. The authors take you, step-by-step, through the entire wonderland of the spectral analysis of time series...they give philosophical as well as practical advice." Journal of the American Statistical Association