bayesRecon: Probabilistic Reconciliation via Conditioning

Provides methods for probabilistic reconciliation of hierarchical forecasts of time series. The available methods include analytical Gaussian reconciliation (Corani et al., 2021) <doi:10.1007/978-3-030-67664-3_13>, MCMC reconciliation of count time series (Corani et al., 2024) <doi:10.1016/j.ijforecast.2023.04.003>, Bottom-Up Importance Sampling (Zambon et al., 2024) <doi:10.1007/s11222-023-10343-y>, methods for the reconciliation of mixed hierarchies (Mix-Cond and TD-cond) (Zambon et al., 2024. The 40th Conference on Uncertainty in Artificial Intelligence, accepted).

Version: 0.3.2
Depends: R (≥ 4.1.0)
Imports: stats, utils, lpSolve (≥ 5.6.18)
Suggests: knitr, rmarkdown, forecast, glarma, scoringRules, testthat (≥ 3.0.0)
Published: 2024-11-04
Author: Dario Azzimonti ORCID iD [aut, cre], Nicolò Rubattu ORCID iD [aut], Lorenzo Zambon ORCID iD [aut], Giorgio Corani ORCID iD [aut]
Maintainer: Dario Azzimonti <dario.azzimonti at gmail.com>
BugReports: https://github.com/IDSIA/bayesRecon/issues
License: LGPL (≥ 3)
URL: https://github.com/IDSIA/bayesRecon
NeedsCompilation: no
Materials: README NEWS
In views: TimeSeries
CRAN checks: bayesRecon results

Documentation:

Reference manual: bayesRecon.pdf
Vignettes: Probabilistic Reconciliation via Conditioning with 'bayesRecon' (source, R code)
Reconciliation of M5 hierarchy with mixed-type forecasts (source, R code)
Properties of the reconciled distribution via conditioning (source, R code)

Downloads:

Package source: bayesRecon_0.3.2.tar.gz
Windows binaries: r-devel: bayesRecon_0.3.1.zip, r-release: bayesRecon_0.3.1.zip, r-oldrel: bayesRecon_0.3.1.zip
macOS binaries: r-release (arm64): bayesRecon_0.3.1.tgz, r-oldrel (arm64): bayesRecon_0.3.1.tgz, r-release (x86_64): bayesRecon_0.3.1.tgz, r-oldrel (x86_64): bayesRecon_0.3.1.tgz
Old sources: bayesRecon archive

Linking:

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