ECMLE: Approximating Evidence via Bounded Harmonic Means
Implements the Elliptical Covering Marginal Likelihood Estimator
(ECMLE), a geometric method for approximating marginal likelihood from
posterior draws and log-posterior evaluations. The method constructs a
collection of non-overlapping ellipsoids in a high-posterior-density
region, computes the covered volume, and combines this with posterior
sample coverage to estimate model evidence. It is designed to stabilize
harmonic-mean-based evidence approximation and can be applied in
multimodal settings. The methodology is described in Naderi et al. (2025)
<doi:10.48550/arXiv.2510.20617>.
| Version: |
0.1.0 |
| Depends: |
R (≥ 3.6.0) |
| Imports: |
IDPmisc, graphics, stats, withr |
| Suggests: |
testthat (≥ 3.0.0), knitr, rmarkdown |
| Published: |
2026-03-26 |
| DOI: |
10.32614/CRAN.package.ECMLE (may not be active yet) |
| Author: |
Dana Naderi [aut, cre],
Christian P. Robert [aut],
Kaniav Kamary [aut],
Darren Wraith [aut] |
| Maintainer: |
Dana Naderi <naderi at ceremade.dauphine.fr> |
| BugReports: |
https://github.com/da-na-deri/ECMLE/issues |
| License: |
GPL-3 |
| URL: |
https://github.com/da-na-deri/ECMLE |
| NeedsCompilation: |
no |
| Materials: |
README, NEWS |
| CRAN checks: |
ECMLE results |
Documentation:
Downloads:
Linking:
Please use the canonical form
https://CRAN.R-project.org/package=ECMLE
to link to this page.