Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Analysing Seasonal Health DataDecomposing Time Series

Analysing Seasonal Health Data: Decomposing Time Series [A useful way to view time series data is as a combination of trend, season and noise. For data that are equally spaced over time (t = 1, …, n) an equation that splits the series into these three parts is 4.1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document} ${Y }_{t} = {\mu }_{t} + {s}_{t} + {\varepsilon }_{t},\qquad t = 1,\ldots ,n,$ \end{document} where μt is the trend, st is the seasonal pattern and ɛt is the random noise (also known as the error or residuals). We assume the residuals are uncorrelated, with a zero mean and constant variance, so \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document} ${\varepsilon }_{t} \sim \textrm{ N}(0,{\sigma }_{\varepsilon }^{2}),\qquad \textrm{ cov}({\varepsilon }_{ t},{\varepsilon }_{k}) = 0,\,t\neq k.$ \end{document}] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

Analysing Seasonal Health DataDecomposing Time Series

Download PDF
35 pages

Loading next page...
 
/lp/springer-journals/analysing-seasonal-health-data-decomposing-time-series-aEN6F9alop
Publisher
Springer Berlin Heidelberg
Copyright
© Springer-Verlag Berlin Heidelberg 2010
ISBN
978-3-642-10747-4
Pages
93 –128
DOI
10.1007/978-3-642-10748-1_4
Publisher site
See Chapter on Publisher Site

Abstract

[A useful way to view time series data is as a combination of trend, season and noise. For data that are equally spaced over time (t = 1, …, n) an equation that splits the series into these three parts is 4.1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document} ${Y }_{t} = {\mu }_{t} + {s}_{t} + {\varepsilon }_{t},\qquad t = 1,\ldots ,n,$ \end{document} where μt is the trend, st is the seasonal pattern and ɛt is the random noise (also known as the error or residuals). We assume the residuals are uncorrelated, with a zero mean and constant variance, so \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document} ${\varepsilon }_{t} \sim \textrm{ N}(0,{\sigma }_{\varepsilon }^{2}),\qquad \textrm{ cov}({\varepsilon }_{ t},{\varepsilon }_{k}) = 0,\,t\neq k.$ \end{document}]

Published: Jan 4, 2010

Keywords: Markov Chain Monte Carlo; Seasonal Pattern; Linear Change; Markov Chain Monte Carlo Sample; Markov Chain Monte Carlo Chain

There are no references for this article.