AR and TVAR Time Series Modelling and Decompositions
- Stationary and Nonstationary/Time-Frequency Analysis -

Raquel Prado & Mike West
(last updates: July 2018)

Matlab code for fitting, analysis and exploration of time series using autoregressive (AR) and time-varying autoregressive (TVAR) models. In addition to model specification, selection and assessment, the software develops time series decompositions to explore underlying latent component structure in observed data -- a general and flexible time-domain approach to "time:frequency" decompositions to elucidate patterns of change over time in frequency structure of stationary and nonstationary series.

Download: Zipped folder with code, utilities and data.

Usage: The Matlab routines are free-standing. The folder includes three examples using time series from neuroscience (EEG) and climatology (SOI), illustrating (i) Bayesian model fitting and selection, (ii) Bayesian inference on underling latent structure via time series decompositions; and (iii) prediction via generation of synthetic futures.

This software is made freely available to any interested user. The author can provide no support nor assistance with implementations beyond the details and examples here, nor extensions of the code for other purposes.

It is understood by the user that neither the author nor Duke University bear any responsibility nor assume any liability for any end-use of this software. It is expected that appropriate credit/acknowledgment be given should the software be included as an element in other software development or in publications.

More software from the West group