ProbReco: Score Optimal Probabilistic Forecast Reconciliation

Training of reconciliation weights for probabilistic forecasts to optimise total energy (or variogram) score using Stochastic Gradient Descent with automatically differentiated gradients. See Panagiotelis, Gamakumara, Athanasopoulos and Hyndman, (2020) <https://www.monash.edu/business/ebs/research/publications/ebs/wp26-2020.pdf> for a description of the methods.

Version: 0.1.0.1
Depends: R (≥ 3.5.0)
Imports: Rcpp (≥ 1.0.2), purrr (≥ 0.3.2), mvtnorm, Rdpack
LinkingTo: Rcpp, RcppEigen, StanHeaders (≥ 2.19.1), BH
Suggests: knitr, rmarkdown, fable, dplyr, tidyr, magrittr, stringi
Published: 2020-09-24
Author: Anastasios Panagiotelis ORCID iD [aut, cre]
Maintainer: Anastasios Panagiotelis <anastasios.panagiotelis at sydney.edu.au>
BugReports: https://github.com/anastasiospanagiotelis/ProbReco/issues
License: GPL-3
URL: https://github.com/anastasiospanagiotelis/ProbReco
NeedsCompilation: yes
Materials: README
In views: TimeSeries
CRAN checks: ProbReco results

Documentation:

Reference manual: ProbReco.pdf
Vignettes: ProbReco-with-fable
ProbReco

Downloads:

Package source: ProbReco_0.1.0.1.tar.gz
Windows binaries: r-devel: ProbReco_0.1.0.1.zip, r-release: ProbReco_0.1.0.1.zip, r-oldrel: ProbReco_0.1.0.1.zip
macOS binaries: r-release (arm64): ProbReco_0.1.0.1.tgz, r-oldrel (arm64): ProbReco_0.1.0.1.tgz, r-release (x86_64): ProbReco_0.1.0.1.tgz, r-oldrel (x86_64): ProbReco_0.1.0.1.tgz
Old sources: ProbReco archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=ProbReco to link to this page.