fdaACF: Autocorrelation Function for Functional Time Series (original) (raw)
Quantify the serial correlation across lags of a given functional time series using the autocorrelation function and a partial autocorrelation function for functional time series proposed in Mestre et al. (2021) <doi:10.1016/j.csda.2020.107108>. The autocorrelation functions are based on the L2 norm of the lagged covariance operators of the series. Functions are available for estimating the distribution of the autocorrelation functions under the assumption of strong functional white noise.
| Version: | 1.0.0 |
|---|---|
| Depends: | R (≥ 3.5.0) |
| Imports: | CompQuadForm, pracma, fda, vars |
| Suggests: | testthat, fields |
| Published: | 2020-10-20 |
| DOI: | 10.32614/CRAN.package.fdaACF |
| Author: | Guillermo Mestre Marcos [aut, cre], José Portela González [aut], Gregory Rice [aut], Antonio Muñoz San Roque [ctb], Estrella Alonso Pérez [ctb] |
| Maintainer: | Guillermo Mestre Marcos <guillermo.mestre at comillas.edu> |
| BugReports: | https://github.com/GMestreM/fdaACF/issues |
| License: | GPL-2 | GPL-3 [expanded from: GPL (≥ 2)] |
| URL: | https://github.com/GMestreM/fdaACF |
| NeedsCompilation: | no |
| Citation: | fdaACF citation info |
| Materials: | NEWS |
| In views: | FunctionalData, TimeSeries |
| CRAN checks: | fdaACF results |
Documentation:
Downloads:
Linking:
Please use the canonical formhttps://CRAN.R-project.org/package=fdaACFto link to this page.