Paramètres
- 148pages
- 6 heures de lecture
En savoir plus sur le livre
This book presents statistical methodologies for analyzing time series data, emphasizing copula-based Markov chain models for serially correlated series. It includes practical examples from various fields such as economics, engineering, finance, and sports to illustrate the methodologies. Designed as an accessible resource for students in economics, management, mathematics, and statistics, it also features stand-alone chapters for researchers. The focus is on parametric models utilizing normal, t, normal mixture, and Poisson distributions, among others. Likelihood-based methods are highlighted as the primary statistical tools for model fitting, with detailed discussions on developing computing techniques for maximum likelihood estimation. The book also covers statistical process control, along with Bayesian and regression methods. To facilitate data analysis, it provides R codes for many of the statistical techniques discussed. The content is organized into chapters that include an overview with data examples, copula and Markov models, estimation and model diagnostics under various distributions, Bayesian estimation for financial data, control charts using copula Markov SPC, and models for count series with excess zeros.
Achat du livre
Copula-Based Markov Models for Time Series, Li-Hsien Sun, Xin-Wei Huang, Mohammed S. Alqawba, Jong-Min Kim, Takeshi Emura
- Langue
- Année de publication
- 2020
- product-detail.submit-box.info.binding
- (souple)
Modes de paiement
Personne n'a encore évalué .
- Titre
- Copula-Based Markov Models for Time Series
- Sous-titre
- Parametric Inference and Process Control
- Langue
- Anglais
- Éditeur
- Springer Nature Singapore
- Publié
- 2020
- Format
- souple
- Pages
- 148
- ISBN13
- 9789811549977
- Séries
- Mots clés
- Nonfiction, Commerce, Affaires & Gestion, Science et Mathématiques, La nature, Mathématiques
- Description
- This book presents statistical methodologies for analyzing time series data, emphasizing copula-based Markov chain models for serially correlated series. It includes practical examples from various fields such as economics, engineering, finance, and sports to illustrate the methodologies. Designed as an accessible resource for students in economics, management, mathematics, and statistics, it also features stand-alone chapters for researchers. The focus is on parametric models utilizing normal, t, normal mixture, and Poisson distributions, among others. Likelihood-based methods are highlighted as the primary statistical tools for model fitting, with detailed discussions on developing computing techniques for maximum likelihood estimation. The book also covers statistical process control, along with Bayesian and regression methods. To facilitate data analysis, it provides R codes for many of the statistical techniques discussed. The content is organized into chapters that include an overview with data examples, copula and Markov models, estimation and model diagnostics under various distributions, Bayesian estimation for financial data, control charts using copula Markov SPC, and models for count series with excess zeros.