Zucchini / MacDonald / Langrock Hidden Markov Models for Time Series

An Introduction Using R, Second Edition
2. Auflage 2016
ISBN: 978-1-4822-5384-9
Verlag: Taylor & Francis
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 398 Seiten

Reihe: Chapman & Hall/CRC Monographs on Statistics & Applied Probability

Hidden Markov Models (HMMs) remains a vibrant area of research in statistics, with many new applications appearing since publication of the first edition. The second edition of this popular reference on the topic has been substantially revised, notably with chapter 8, extensions of the basic HMM, now expanded to four chapters with many more models included. There are also lots of new applications, extended software guidelines and code and many minor improvements throughout the book.

Autoren/Hrsg.

Zucchini, Walter

MacDonald, Iain L.

Langrock, Roland

Fachgebiete

• Mathematik | Informatik Mathematik Stochastik

Inhaltsverzeichnis

Model Structure, Properties and Methods. Preliminaries: Finite Mixtures and Markov Chains. Hidden Markov Models: Definition and Properties. Estimation by Direct Maximization of the Likelihood. Estimation by the Em Algorithm. Forecasting, Decoding and State Prediction. Model Selection and Checking. Bayesian Inference for Poisson-Hmms. Extensions of the Basic Hidden Markov Model. Hmms with General State-Dependent Distribution, Both Univariate and Multivariate. Hmms with Nonstandard Dependence Structure. Hmms with Covariates and Hmms for Longitudinal Data. Hmms with Continuous-Valued Latent Process. Applications. R Software Available for Hmms. Epileptic Seizures. Eruptions of the Old Faithful Geyser. Models for Animal Movement. Wind Direction at Koeberg. Models for Financial Series, Including Stochastic Volatility Models. Births at Edendale Hospital. Homicides and Suicides in Cape Town. Animal Behavior Model with Feedback. Capture-Recapture Models. Animal Abundance Estimation. Appendices.