Package: ECMLE
Type: Package
Title: Approximating Evidence via Bounded Harmonic Means
Version: 0.1.0
Authors@R: c(
    person(given = "Dana",
           family = "Naderi",
           email = "naderi@ceremade.dauphine.fr",
           role = c("aut", "cre")),
    person(given = c("Christian", "P."),
           family = "Robert",
           role = "aut"),
    person(given = "Kaniav",
           family = "Kamary",
           role = "aut"),
    person(given = "Darren",
           family = "Wraith",
           role = "aut")
  )
Description: 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>.
License: GPL-3
Encoding: UTF-8
Depends: R (>= 3.6.0)
Imports: IDPmisc, graphics, stats, withr
Suggests: testthat (>= 3.0.0), knitr, rmarkdown
VignetteBuilder: knitr
Config/testthat/edition: 3
URL: https://github.com/da-na-deri/ECMLE
BugReports: https://github.com/da-na-deri/ECMLE/issues
NeedsCompilation: no
Packaged: 2026-03-23 11:15:51 UTC; naderi
Author: Dana Naderi [aut, cre],
  Christian P. Robert [aut],
  Kaniav Kamary [aut],
  Darren Wraith [aut]
Maintainer: Dana Naderi <naderi@ceremade.dauphine.fr>
Repository: CRAN
Date/Publication: 2026-03-26 10:10:12 UTC
Built: R 4.6.0; ; 2026-04-23 01:18:16 UTC; windows
