Fundamentals of Statistical Processing

For practicing engineers and scientists who design and analyze signal processing systems, i.e., to extract information from noisy signals ― radar engineer, sonar engineer, geophysicist, oceanographer, biomedical engineer, communications engineer, economist, statistician, physicist, etc.

A unified presentation of parameter estimation for those involved in the design and implementation of statistical signal processing algorithms.

For those involved in the design and implementation of signal processing algorithms, this book strikes a balance between highly theoretical expositions and the more practical treatments, covering only those approaches necessary for obtaining an optimal estimator and analyzing its performance. Author Steven M. Kay discusses classical estimation followed by Bayesian estimation, and illustrates the theory with numerous pedagogical and real-world examples. Special features include over 230 problems designed to reinforce basic concepts and to derive additional results; summary chapter containing an overview of all principal methods and the rationale for choosing a particular one; unified treatment of Wiener and Kalman filtering; estimation approaches for complex data and parameters; and over 100 examples, including real-world applications to high resolution spectral analysis, system identification, digital filter design, adaptive noise cancelation, adaptive beamforming, tracking and localization, and more. Students as well as practicing engineers will find Fundamentals of Statistical Signal Processing an invaluable introduction to parameter estimation theory and a convenient reference for the design of successful parameter estimation algorithms.