Hidden Markov and Other Models for Discrete- valued Time Series (Chapman & Hall/CRC Monographs on Statistics & Applied Probability)

Discrete-valued time series are common in practice, but methods for their analysis are not well-known. In recent years, methods have been developed which are specifically designed for the analysis of discrete-valued time series. Hidden Markov and Other Models for Discrete-Valued Time Series introduces a new, versatile, and computationally tractable class of models, the "hidden Markov" models. It presents a detailed account of these models, then applies them to data from a wide range of diverse subject areas, including medicine, climatology, and geophysics. This book will be invaluable to researchers and postgraduate and senior undergraduate students in statistics. Researchers and applied statisticians who analyze time series data in medicine, animal behavior, hydrology, and sociology will also find this information useful.

The book is well written. It gives a nice description of methods proposed for analysis of discrete-valued time series, their theoretical background and examples of applications. The book can be recommended to statisticians who analyze data as well as to students and teachers. It can be used as very good material for seminars and special lectures.
-Zentralblatt für Mathematik
...the authors should be applauded for providing this concise survey of HMMs and other discrete-valued time series models that have been scattered in the literature...I recommend Hidden Markov and Other Models for Discrete-Valued Time Series to time series analysts who are interested in discrete-valued dependent data.
-Journal of the ASA, December 1998