Reprint

Discrete-Valued Time Series

Edited by
March 2024
222 pages
  • ISBN978-3-7258-0477-1 (Hardback)
  • ISBN978-3-7258-0478-8 (PDF)

This book is a reprint of the Special Issue Discrete-Valued Time Series that was published in

Chemistry & Materials Science
Computer Science & Mathematics
Physical Sciences
Summary

The analysis and modeling of time series has been an active research area for more than 100 years, with the main focus on time series having a continuous range consisting of real numbers or real vectors. It took until the 1980s for the first papers on discrete-valued time series to appear. In the 2000s, a rapid increase in research activity was noted, but only in the last few years was a certain maturity and consolidation of the area of discrete-valued time series observed. This reprint is a collection of articles on a wide range of topics on discrete-valued time series (especially count time series), covering stochastic models and methods for their analysis, univariate and multivariate time series, applications of time series methods to risk analysis, statistical process control, and many more. The proposed approaches and concepts are thoroughly discussed and illustrated with several real-world data examples.

Format
  • Hardback
License
© 2022 by the authors; CC BY-NC-ND license
Keywords
Granger causality; conditional mutual information; mixed embedding; symbol sequences; discrete-valued time series; financial complex network; autoregressive model; count time series; INAR bootstrap; partial autocorrelation function; Yule–Walker equations; CMPB thinning operator; bounded time series; CMPBAR model; under-dispersion; equi-dispersion; over-dispersion; INARCH model; saddlepoint approximation; thinning-based model; time series of counts; discrete-time Markov chain; TP2 transition probability matrix; Kalmykov order; statistical process control; run length; Bayesian estimation; censored time series; convolution closed infinitely divisible; Poisson INAR(1) model; risk model; stochastic premiums; INAR(1) process; INMA(1) process; ruin probability; integer-valued time series; thinning operator; observation-driven; ergodicity; interval estimation; INGARCH; count time series; conditional distribution; dynamic structure; robust estimation; n onlinear state space model; iterated extended Kalman filter; Bayesian filtering; count time series; singular value decomposition; n/a