Bayesian multiscale analysis for time series data

Tor Arne Øigård*, Haavard Rue, Fred Godtliebsen

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

23 Scopus citations

Abstract

A recently proposed Bayesian multiscale tool for exploratory analysis of time series data is reconsidered and umerous important improvements are suggested. The improvements are in the model itself, the algorithms to analyse it, and how to display the results. The consequence is that exact results can be obtained in real time using only a tiny fraction of the CPU time previously needed to get approximate results. Analysis of both real and synthetic data are given to illustrate our new approach. Multiscale analysis for time series data is a useful tool in applied time series analysis, and with the new model and algorithms, it is also possible to do such analysis in real time.

Original languageEnglish (US)
Pages (from-to)1719-1730
Number of pages12
JournalComputational Statistics and Data Analysis
Volume51
Issue number3
DOIs
StatePublished - Dec 1 2006

Keywords

  • Gaussian Markov random fields
  • Multiscale analysis
  • SiZer
  • Sparse matrices
  • Statistical inference
  • Time series analysis

ASJC Scopus subject areas

  • Statistics and Probability
  • Computational Mathematics
  • Computational Theory and Mathematics
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Bayesian multiscale analysis for time series data'. Together they form a unique fingerprint.

Cite this