Time Series Analysis for the State-Space Model with R/Stan

Provides a comprehensive and concrete illustration for the state-space model
Covers whole solutions through a consistent Bayesian approach: the batch method by MCMC using Stan and sequential ones by Kalman/particle filter using R
Presents advanced topics such as real-time structural change detection with the horseshoe prior

Provides a comprehensive and concrete illustration for the state-space model Covers whole solutions through a consistent Bayesian approach: the batch method by MCMC using Stan and sequential ones by Kalman/particle filter using R Presents advanced topics such as real-time structural change detection with the horseshoe prior

Autorentext

Junichiro Hagiwara received the B.E., M.E., and Ph.D. degrees from Hokkaido University, Sapporo, Japan, in 1990, 1992, and 2016, respectively. He joined the Nippon Telegraph and Telephone Corporation in April 1992 and transferred to NTT Mobile Communications Network, Inc. (currently NTT DOCOMO, INC.) in July 1992. Later, he became involved in the research and development of mobile communication systems. His current research interests are in the application of stochastic theory to the communication domain. He is currently a visiting professor at Hokkaido University.

Inhalt
Introduction.- Fundamental of probability and statistics.- Fundamentals of handling time series data with R.- Quick tour of time series analysis.- State-space model.- State estimation in the state-space model.- Batch solution for linear Gaussian state-space model.- Sequential solution for linear Gaussian state-space model.- Introduction and analysis examples of a well-known component model.- Batch solution for general state-space model.- Sequential solution for general state-space model.- Example of applied analysis in general state-space model.