R Observatory: Metrics for bmgarch version 2.1.0

Balamuta, James Joseph

doi:10.5281/zenodo.21843040

bmgarch

2.1.0Package record

Bayesian Multivariate GARCH Models

0packages depend

5.4Kdownloads / year

–test coverage

13/13flavors OK

Overview

About

Maintained by Philippe RastCRAN page ↗GitHub ↗Issues ↗

Fit Bayesian multivariate GARCH models using 'Stan' for full Bayesian inference. Generate (weighted) forecasts for means, variances (volatility) and correlations. Currently DCC(P,Q), CCC(P,Q), pdBEKK(P,Q), and BEKK(P,Q) parameterizations are implemented, alongside a constant covariance baseline (that can be used for testing whether GARCH is warranted), based either on a multivariate gaussian normal or student-t distribution. DCC and CCC models are based on Engle (2002) doi:10.1198/073500102288618487 and Bollerslev (1990). The BEKK parameterization follows Engle and Kroner (1995) doi:10.1017/S0266466600009063 while the pdBEKK as well as the estimation approach for this package is described in Rast et al. (2020) doi:10.31234/osf.io/j57pk. The fitted models contain 'rstan' objects and can be examined with 'rstan' functions.

Changes in 2.1.0

cmdstanr backend support

bmgarch() now accepts backend = "cmdstanr" in addition to the default "rstan". Both MCMC (NUTS) and variational Bayes (sampling_algorithm = "VB") are supported with the new backend.
summary(), print(), plot(), forecast(), fitted(), loo(), and model_weights() all work with cmdstanr-fitted objects.
Stan function a_b_scale_jacobian renamed to a_b_scale_log_jac to avoid a future name collision with Stan 2.39's reserved _jacobian suffix (affects inst/stan/functions/jacobian.stan).
The iterations argument now defaults to 2000 for MCMC and 30000 for VB when left unspecified. Previously the single default of 2000 was too low for ADVI gradient ascent.

Show all changes in 2.1.0Hide the rest of the changes in 2.1.0

The backend field is stored in every bmgarch object so that loo() refits and other operations that call back into bmgarch() automatically use the same backend.
Threading defaults: cmdstanr models compiled with stan_threads = TRUE now default to threads_per_chain = 1 (MCMC) and threads = 1 (VB). Users can override via ....

Bug fixes

Fixed ensemble covariance underestimation in .weighted_samples(). The between-model variance term required by the law of total variance, Σ_m w_m (μ̂_m − μ̂_mix)(μ̂_m − μ̂_mix)ᵀ, is now added to the weighted combination of H and H_forecasted. This corrects the ensemble posterior predictive covariance for both backcasts and forecasts whenever models with differing mean structures are combined. The fix is a no-op for single-model objects.
model_weights() and loo() now work with cmdstanr objects: log_lik extraction and chain/iteration metadata no longer rely on rstan S4 slot access (@sim).
Weighted forecasts (forecast(..., weights = mw)) now work with cmdstanr backends via a new .extract_param_list() helper that replicates rstan::extract() output for cmdstanr draw objects.
Forecast draws passed to rstan::gqs() are now correctly extracted via posterior::as_draws_matrix() for cmdstanr fits, fixing a "no dimnames" error.

Tests

Added tests/testthat/test-backends.R covering summary, forecast, and model_weights for all three combinations: rstan/MCMC, cmdstanr/MCMC, and cmdstanr/VB on a CCC model.

From NEWS.md in the release

Install

R (CRAN)pak (dev)Ubuntu (r2u)Fedora (COPR)openSUSE (OBS)

install.packages("bmgarch", repos = "https://cloud.r-project.org/")

Installs the current CRAN release. Prebuilt binaries on Windows and macOS.

if (!requireNamespace("pak", quietly = TRUE))
  install.packages("pak", repos = "https://cloud.r-project.org/")
pak::pak("ph-rast/bmgarch")

Development version from ph-rast/bmgarch. Installs pak first if it is not already available.

Release

# enable cranapt (r2u) if it is not already set up, then install
grep -rqs r2u.stat.illinois.edu /etc/apt/sources.list /etc/apt/sources.list.d/ \
  || curl -fsSL https://raw.githubusercontent.com/eddelbuettel/r2u/master/inst/scripts/add_cranapt_noble.sh | sudo bash
sudo apt install -y r-cran-bmgarch

Fast Ubuntu binaries via r2u (no compilation). The cranapt setup runs once and is skipped when it is already enabled. We list this channel from recorded r2u download activity rather than from a live index of the repository, so treat it as last known rather than guaranteed.

bspm (used by r2u) also needs make: sudo apt install make

# enable the iucar/cran COPR if it is not already present, then install
ls /etc/yum.repos.d/*iucar*cran*.repo >/dev/null 2>&1 \
  || sudo dnf copr enable -y iucar/cran
sudo dnf install -y R-CRAN-bmgarch

RPMs from the iucar/cran COPR, rebuilt from CRAN.

For install.packages() integration in R, also: sudo dnf install R-CoprManager

# add the autoCRAN OBS repo (Tumbleweed) if it is missing, then install
zypper -q lr | grep -qi autoCRAN \
  || sudo zypper addrepo https://download.opensuse.org/repositories/devel:/languages:/R:/autoCRAN/openSUSE_Tumbleweed/devel:languages:R:autoCRAN.repo
sudo zypper install -y R-bmgarch

RPMs auto-built from CRAN on openSUSE OBS (Tumbleweed). We list this channel from recorded autoCRAN download activity rather than from a live index of the repository, so treat it as last known rather than guaranteed.

Health

CRAN checks

13OK

CRAN check page ↗

Slowest check: 44.0 min · r-oldrel-windows-x86_64

Status changes

OK13 OK2026-08-05
NOTE12 OK, 1 NOTE2026-08-01
OK13 OK2026-07-29
ERROR12 OK, 1 ERROR2026-07-27
OK13 OK2026-05-28

Show 3 earlier changesHide 3 earlier changes

NOTE14 NOTE2026-04-22
ERROR13 NOTE, 1 ERROR2026-04-18
NOTE14 NOTE2026-03-10

Advisories

none known

How this is measured·How advisories are found

Documentation

In release 2.1.0

READMEYes · 4,729 wordsVignettesNoNEWSYes · 100% structured · mentions 2.1.0Citation fileNoWebsitenot declared in DESCRIPTION

Help pages: 44 (26 internal)includes a package overview page
Examples that run: 0%5 never run
Exported functions with examples: 80%
Documented parameters: 100%
Return-value docs: 100%
Help pages citing references: 9% with a bibliography file

How these are measured

Downloads

5.4K

CRAN downloads in the past year

Rank #5,173 · ~15/day · ~449/mo

Releases R versions

Daily download trend is not available in this view yet.

51830 days

1.6K90 days

5.4K1 year

Compare downloads with other packages →

Also on516 r2u39 autocran110 c2d4u

How downloads are counted

Repository

ph-rast/bmgarch ↗Account: ph-rast

18Stars

11Forks

0Open issues

0Open PRs

1Releases

515Commits

5Commit identities

515 commits · Last activity 2026-07-07

Responsiveness

How these are sampled

PRs merged (all time): 94%
Median days to close, 50 most recently updated closed issues: 8
Median days to close, 50 most recently updated closed PRs: 0

Stars over time

2025-04-23 · 182026-07-07 · 18

How these are measured

PracticesBeta

8 development-tooling and community-health practices detected across 5 families in the upstream repository

Checks run against github.com/ph-rast/bmgarch on 2026-10-21.

Continuous integration (3)

GitHub ActionsR CMD check workflowTravis CI (config file)

The R CMD check workflow runs on Linux, macOS and Windows

Governance and community (2)

Code of conductContributing guide

Docs source (1)

README.Rmd

Coverage (1)

.covrignore

Show all practicesHide 1 practice

CRAN release process (1)

cran-comments.md

How this is detected·Detection ruleset v4 (2026-10-20)

Dependencies

Declared dependencies

17 external dependencies (excludes base and recommended)

Installing bmgarch adds 58 packages (30 with compiled code, 50 MB of source tarballs). Heaviest: BH 14 MB, ggplot2 6.0 MB, loo 2.7 MB.

Depends (3)

R >= 4.0.0methodsRcpp

Imports (7)

forecast ggplot2 looMASSRdpack rstan rstantools

LinkingTo (7)

BH Rcpp RcppParallel RcppEigen RcppParallel rstan (>= 2.26.0)StanHeaders

Suggests (3)

cmdstanr posterior testthat

Enhances (0)

none

Dependency license breakdown →

Reverse dependencies

0direct

0indirect

Nothing depends on this yet.

How these are counted

Code & Tests

Datasets

People & History

People (2)

Philippe Rast

Author, Maintainer since 1.0.0 (2020)

Stephen Martin

Author

Releases (5)

Pick two releases to compare their code metrics.

2.1.0Latest
record
2026-05-21 · current release · diff ↗
R
R 4.6.0 released · 2026-04-24
R
R 4.5.0 released · 2025-04-11
R
R 4.4.0 released · 2024-04-24
2.0.0
record
2023-09-12 · diff ↗
R
R 4.3.0 released · 2023-04-21
R
R 4.2.0 released · 2022-04-22
1.1.0
record
2021-12-14 · diff ↗
1.0.1
record
2021-06-14 · diff ↗
R
R 4.1.0 released · 2021-05-18
1.0.0
record
2020-09-17
R
R 4.0.0 released · 2020-04-24

Package metadata

First published: 2020-09-17
Total releases: 5 / 6 yrs
License: GPL (>= 3) OSI
Additional repositories: stan-dev.r-universe.dev
Minimum R: ≥ 4.0.0
Bundled data: 40 KB / 2 files
Download size: 208 KB

Appears in task views

Empirical Finance

Cite

Cite this package

Run in R for the authors' preferred citation:

citation("bmgarch")

Format

Rast, P., & Martin, S. (2026). bmgarch: Bayesian Multivariate GARCH Models (Version 2.1.0) [Computer software]. https://doi.org/10.32614/CRAN.package.bmgarch

This package has no citation file, so citation() returns this entry built from DESCRIPTION.

Cite the R Observatory

For a number measured here: a download total, a coverage figure, an archival date.

Format

APA

Balamuta, J. J. (2026). R Observatory: Metrics for bmgarch version 2.1.0 [Data set]. HJJB, LLC. Data release v2026-10-23. https://doi.org/10.5281/zenodo.21843040

From data release v2026-10-23, which the citation names so these numbers can be found later. More on citing and the projects behind them.

Report a problem with this page →