Description: This text provides a self-contained, "no frills," mathematically rigorous derivation from first principles of all basic Kalman filter recursions. This approach relies on a pared-down version of more general state-space models found most often in the literature. Such simplification saves notational complexity without sacrificing conceptual understanding. The rigor found in the book ensures a fundamental understanding of how the Kalman filter actually works, which builds confidence for those employing the filter in their research and writing code to implement it in practice. The author provides implementations of the Kalman filter in Java available for download from his Web site.
Review Quotes: "We strongly recommend Eubank's book. It is a masterpiece of exposition, in a class by itself (there are no similar books at a truly introductory level), which makes basic understanding and applying the Kalman filter as simple as possible. It is written in a way that motivates the readers' interest, a pleasure (enjoyable) to read; it provides in an interesting and concise way the right amount of detail. One of the strengths of the book is the author's love of and enthusiasm for the subject. It clearly shows the author's concern with making as easy as possible the reader's path to learning." - Prof. Emanuel Parzen, Texas A&M University "develops the algorithmic aspects of Kalman filtering for state space models. The Basic tool is best linear unbiased prediction, which is immediately interpreted in terms of the Cholesky factorization of the relevant variance-covariance matrices. This also leads to an easy presentation of the 'backward' filtering step when one wishes to solve smoothing problems "The author gives a comprehensive (and comprehensible) account of how the Kalman filter may be adapted to handle [diffuse priors]. This is no mean feat, as the literature on diffuse priors is scattered and algorithms are often presented with little motivation, other than that they work. "This is a do-it-yourself text. It treats Kalman filtering for two fundamental examples in detail: ARMA models for time-series and Brownian motion in white noise. The complete algorithms are presented, ready for computer implementation, and more importantly, ready for modification. This will give graduate students and researchers a flying start for treating their own applications. "The author has given us a rareglimpse of what happens when someone wants to get to the bottom of things: one senses his wonder about these beautiful and beautifully efficient algorithms." -Paul Eggermont, Department of Food & Resource Economics, University of Delaware