Package: GeomComb 1.0

Christoph E. Weiss

GeomComb: (Geometric) Forecast Combination Methods

Provides eigenvector-based (geometric) forecast combination methods; also includes simple approaches (simple average, median, trimmed and winsorized mean, inverse rank method) and regression-based combination. Tools for data pre-processing are available in order to deal with common problems in forecast combination (missingness, collinearity).

Authors:Christoph E. Weiss, Gernot R. Roetzer

GeomComb_1.0.tar.gz
GeomComb_1.0.tar.gz(r-4.5-noble)GeomComb_1.0.tar.gz(r-4.4-noble)
GeomComb_1.0.tgz(r-4.4-emscripten)GeomComb_1.0.tgz(r-4.3-emscripten)
GeomComb.pdf |GeomComb.html✨
GeomComb/json (API)

# Install 'GeomComb' in R:

install.packages('GeomComb', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/ceweiss/geomcomb/issues

On CRAN:

1.70 score 161 downloads 17 exports 58 dependencies

Last updated 8 years agofrom:80e5e0db25. Checks:2 OK, 1 NOTE. Indexed: yes.

Target	Result	Latest binary
Doc / Vignettes	OK	Mar 28 2025
R-4.5-linux	NOTE	Mar 28 2025
R-4.4-linux	OK	Mar 28 2025

Exports:auto_combine comb_BG comb_CLS comb_EIG1 comb_EIG2 comb_EIG3 comb_EIG4 comb_InvW comb_LAD comb_MED comb_NG comb_OLS comb_SA comb_TA comb_WA cs_dispersion foreccomb

Dependencies:cli codetools colorspace curl fansi farver foreach forecast ForecastCombinations fracdiff gam generics ggplot2 glue GPArotation gtable isoband iterators jsonlite labeling lattice lifecycle lmtest magrittr MASS Matrix MatrixModels mgcv mnormt mtsdi munsell nlme nnet pillar pkgconfig psych quadprog quantmod quantreg R6 RColorBrewer Rcpp RcppArmadillo rlang scales SparseM survival tibble timeDate tseries TTR urca utf8 vctrs viridisLite withr xts zoo

Citation

To cite package ‘GeomComb’ in publications use:

Weiss CE, Roetzer GR (2016). GeomComb: (Geometric) Forecast Combination Methods. R package version 1.0, https://CRAN.R-project.org/package=GeomComb.

ATTENTION: This citation information has been auto-generated from the package DESCRIPTION file and may need manual editing, see ‘help("citation")’.

Corresponding BibTeX entry:

  @Manual{,
    title = {GeomComb: (Geometric) Forecast Combination Methods},
    author = {Christoph E. Weiss and Gernot R. Roetzer},
    year = {2016},
    note = {R package version 1.0},
    url = {https://CRAN.R-project.org/package=GeomComb},
  }

Readme and manuals

GeomComb

(Geometric) Forecast Combination in R

(written by Chris E. Weiss and Gernot Roetzer)

The R package GeomComb presents functions to pool individual model forecasts using geometric (eigenvector-based) forecast combination methods. The package also provides functions for simple forecast combination methods (inverse rank approach, simple average, trimmed mean, and winsorized mean - including the option of a criterion-based optimisation of the trimming factor) and regression-based forecast combination methods.

The forecast combination methods allow for 3 different input types:

Only training set
Training set + future forecasts
Full training + test set

Accuracy measures are provided accordingly, summary and plot functions have been created for the S3 classes. The function auto.combine() is an automated selection of the best combination method based on criterion optimisation in the training set.

Installation

The package is still in the development stage -- updates on CRAN release will be shared here in the future.

If you are interested in using the provided functions for your research in the meantime, you are welcome to email us: info@ceweiss.com

You can also install the development version from Github

# install.packages("devtools")
devtools::install_github("ceweiss/GeomComb")

License

This package is free and open source software, licensed under GPL (>= 2).

Help Manual

Help page	Topics
Automated Forecast Combination	auto_combine
Bates/Granger (1969) Forecast Combination Approach	comb_BG
Constrained Least Squares Forecast Combination	comb_CLS
Standard Eigenvector Forecast Combination	comb_EIG1
Bias-Corrected Eigenvector Forecast Combination	comb_EIG2
Trimmed Eigenvector Forecast Combination	comb_EIG3
Trimmed Bias-Corrected Eigenvector Forecast Combination	comb_EIG4
Inverse Rank Forecast Combination	comb_InvW
Least Absolute Deviation Forecast Combination	comb_LAD
Median Forecast Combination	comb_MED
Newbold/Granger (1974) Forecast Combination	comb_NG
Ordinary Least Squares Forecast Combination	comb_OLS
Simple Average Forecast Combination	comb_SA
Trimmed Mean Forecast Combination	comb_TA
Winsorized Mean Forecast Combination	comb_WA
Compute Cross-Sectional Dispersion	cs_dispersion
Format Raw Data for Forecast Combination	foreccomb
Plot results from forecast combination model	plot.foreccomb_res
Summary of Forecast Combination	print.foreccomb_res_summary summary.foreccomb_res