Multivariate, Locally Stationary Wavelet Process Estimation

Tools for analysing multivariate time series with wavelets. This includes: simulation of a multivariate locally stationary wavelet (mvLSW) process from a multivariate evolutionary wavelet spectrum (mvEWS); estimation of the mvEWS, local coherence and local partial coherence. See Park, Eckley and Ombao (2014) for details.


News

Changelog for mvLSW R package

############################### Version 1.0 uploaded 23/02/2017


Version | Decription | Suggested/Identified by

1.1 (24/02/2017) | Support time series classes "zoo" and "xts" | JSS reviewer | Add S3 print() and simulate() commands | JSS reviewer | Remove internal only commands from NAMESPACE | JSS reviewer

1.2 (04/08/2017) | Correct error when tol=-Inf in mvEWS() to not apply regularisation | Simon Taylor (authour) | Corrections and general edits to manual pages | JSS reviewer | Convert Asymp_Quantile to ApxCI, make appropriate edits to plot.mvLSW. | JSS reviewer

1.2.1 (18/08/2017) | Allow tol=NA in mvEWS() to specify not to apply positiveness correction | Tim Park

1.2.2 (23/10/2018) | Correct error in RawPeriodogram when defining attributes of output | Simon Taylor | Added Vignette to package | Idris Eckley

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("mvLSW")

1.2.3 by Simon Taylor, 2 years ago


Browse source code at https://github.com/cran/mvLSW


Authors: Simon Taylor [aut, cre] , Tim Park [aut] , Idris Eckley [ths] , Rebecca Killick [ctb]


Documentation:   PDF Manual  


Task views: Time Series Analysis


GPL (>= 3) license


Depends on fields, wavethresh, xts, zoo


See at CRAN