| mvLSWimpute-package {mvLSWimpute} | R Documentation |
Imputation Methods for Multivariate Locally Stationary Time Series
Description
Implementation of imputation techniques based on locally stationary wavelet time series forecasting methods from Wilson, R. E. et al. (2021) <doi:10.1007/s11222-021-09998-2>.
Details
The DESCRIPTION file:
| Package: | mvLSWimpute |
| Type: | Package |
| Title: | Imputation Methods for Multivariate Locally Stationary Time Series |
| Version: | 0.1.1 |
| Date: | 2022-08-15 |
| Author: | Rebecca Wilson [aut], Matt Nunes [aut, cre], Idris Eckley [ctb, ths], Tim Park [ctb] |
| Authors@R: | c(person("Rebecca", "Wilson", role = "aut"), person("Matt", "Nunes", role=c("aut","cre"), email="nunesrpackages@gmail.com"), person("Idris", "Eckley", role=c("ctb","ths")), person("Tim","Park", role="ctb")) |
| Maintainer: | Matt Nunes <nunesrpackages@gmail.com> |
| Description: | Implementation of imputation techniques based on locally stationary wavelet time series forecasting methods from Wilson, R. E. et al. (2021) <doi:10.1007/s11222-021-09998-2>. |
| License: | GPL-2 |
| Depends: | wavethresh, mvLSW |
| Imports: | binhf, xts, zoo, imputeTS, utils |
Index of help topics:
correct_per Function to smooth the raw wavelet periodogram
form_lacv_forward Function to form the local autocovariance array
for the forecasting / backcasting step.
haarWT Function to apply the (univariate) Haar wavelet
transform
mvLSWimpute-package Imputation Methods for Multivariate Locally
Stationary Time Series
mv_impute Function to apply the mvLSWimpute method and
impute missing values in a multivariate locally
stationary time series
pdef Function to regularise the LWS matrix.
pred_eq_forward Function to form the prediction equations for
the forecasting / backcasting step.
smooth_per Function to smooth the raw wavelet periodogram
using the default 'mvLSW' routine.
spec_estimation Function to estimate the Local Wavelet Spectral
matrix for a multivariate locally stationary
time series containing missing values
The main routine of the package is mv_impute which performs forward or forward and backward imputation of locally stationary multivariate time series, using one-step ahead forecasting (and backcasting).
Author(s)
Rebecca Wilson [aut], Matt Nunes [aut, cre], Idris Eckley [ctb, ths], Tim Park [ctb]
Maintainer: Matt Nunes <nunesrpackages@gmail.com>
References
Wilson, R. E., Eckley, I. A., Nunes, M. A. and Park, T. (2021) A wavelet-based approach for imputation in nonstationary multivariate time series. _Statistics and Computing_ *31* Article 18, doi:10.1007/s11222-021-09998-2.