An implementation of a number of Global Trend models for time series forecasting
that are Bayesian generalizations and extensions of some Exponential Smoothing models.
The main differences/additions include 1) nonlinear global trend, 2) Student-t error
distribution, and 3) a function for the error size, so heteroscedasticity. The methods
are particularly useful for short time series. When tested on the well-known M3 dataset,
they are able to outperform all classical time series algorithms. The models are fitted
with MCMC using the 'rstan' package.
| Version: |
0.2-3 |
| Depends: |
R (≥ 3.4.0), Rcpp (≥ 0.12.0), methods, rstantools, forecast, truncnorm |
| Imports: |
rstan (≥ 2.26.0), sn |
| LinkingTo: |
StanHeaders (≥ 2.26.0), rstan (≥ 2.26.0), BH (≥ 1.66.0), Rcpp (≥ 0.12.0), RcppEigen (≥ 0.3.3.3.0), RcppParallel (≥
5.0.2) |
| Suggests: |
doParallel, foreach, knitr, rmarkdown, Mcomp, RODBC, dplyr, ggplot2 |
| Published: |
2025-04-30 |
| DOI: |
10.32614/CRAN.package.Rlgt |
| Author: |
Slawek Smyl [aut],
Christoph Bergmeir [aut, cre],
Erwin Wibowo [aut],
To Wang Ng [aut],
Xueying Long [aut],
Alexander Dokumentov [aut],
Daniel Schmidt [aut],
Trustees of Columbia University [cph] (tools/make_cpp.R,
R/stanmodels.R) |
| Maintainer: |
Christoph Bergmeir <christoph.bergmeir at monash.edu> |
| License: |
GPL-3 |
| URL: |
https://github.com/cbergmeir/Rlgt |
| NeedsCompilation: |
yes |
| SystemRequirements: |
GNU make |
| Materials: |
ChangeLog |
| In views: |
TimeSeries |
| CRAN checks: |
Rlgt results |