ABSTRACT

Reveals How HMMs Can Be Used as General-Purpose Time Series ModelsImplements all methods in RHidden Markov Models for Time Series: An Introduction Using R applies hidden Markov models (HMMs) to a wide range of time series types, from continuous-valued, circular, and multivariate series to binary data, bounded and unbounded counts, and categorical o

part |2 pages

PART ONE Model structure, properties and methods

chapter 1|26 pages

Preliminaries: mixtures and Markov chains

chapter 4|16 pages

Estimation by the EM algorithm

chapter 5|14 pages

Forecasting, decoding and state prediction

chapter 6|14 pages

Model selection and checking

chapter 7|12 pages

Bayesian inference for Poisson–HMMs

part |2 pages

PART TWO Applications

chapter 9|6 pages

Epileptic seizures

chapter 10|14 pages

Eruptions of the Old Faithful geyser

chapter 11|12 pages

Drosophila speed and change of direction

chapter 12|14 pages

Wind direction at Koeberg

chapter 13|18 pages

Models for financial series

chapter 14|10 pages

Births at Edendale Hospital

chapter 16|20 pages

Animal behaviour model with feedback