Package: lopensemble
Title: Create Mixture Models From Predictive Samples
Version: 0.1.2.9000
Authors@R: 
    c(person(given = "Nikos",
             family = "Bosse",
             role = c("aut", "cre", "cph"),
             email = "nikosbosse@gmail.com",
             comment = c(ORCID = "0000-0002-7750-5280")),
      person(given = "Yuling",
             family = "Yao",
             role = c("aut"),
             email = "yy2619@columbia.edu"),
      person(given = "Sam", 
            family = "Abbott",
            role = c("aut"),
            email = "contact@samabbott.co.uk",
            comment = c(ORCID = "0000-0001-8057-8037")), 
      person(given = "Sebastian",
             family = "Funk",
             role = c("aut"),
             email = "sebastian.funk@lshtm.ac.uk",
             comment = c(ORCID = "0000-0002-2842-3406")))
Description: Combines predictions from individual time series or panel
        data models into an ensemble using stacking (Yao, Vehtari,
        Simpson, and Gelman (2018) <doi:10.1214/17-BA1091>) based on
        the Continuous Ranked Probability Score (CRPS) (Gneiting and
        Raftery (2007) <doi:10.1198/016214506000001437>) over k-step
        ahead predictions. Predictions must be predictive distributions
        represented by samples, typically posterior predictive
        simulation draws from a Markov chain Monte Carlo (MCMC)
        algorithm. Given training data with observed values and
        predictive samples from different models, optimal stacking
        weights are computed to minimize expected cross-validation
        predictive error. These weights can then be used to generate
        samples from the mixture model by drawing from individual model
        predictions in the correct proportions.
License: MIT + file LICENSE
Encoding: UTF-8
LazyData: true
Biarch: true
Depends: R (>= 3.5.0)
Imports: data.table, cmdstanr
Remotes: stan-dev/cmdstanr
SystemRequirements: CmdStan (>=2.29)
RoxygenNote: 7.3.2
Suggests: knitr, rmarkdown, testthat (>= 3.0.0), scoringutils
VignetteBuilder: knitr
Config/testthat/edition: 3
Repository: https://epiforecasts.r-universe.dev
Date/Publication: 2026-01-30 14:51:24 UTC
RemoteUrl: https://github.com/epiforecasts/lopensemble
RemoteRef: v0.1.3
RemoteSha: cd260b8a8dac089bd8d188fc32ef937f988ad296
NeedsCompilation: no
Packaged: 2026-07-04 12:19:20 UTC; root
Author: Nikos Bosse [aut, cre, cph] (ORCID:
    <https://orcid.org/0000-0002-7750-5280>),
  Yuling Yao [aut],
  Sam Abbott [aut] (ORCID: <https://orcid.org/0000-0001-8057-8037>),
  Sebastian Funk [aut] (ORCID: <https://orcid.org/0000-0002-2842-3406>)
Maintainer: Nikos Bosse <nikosbosse@gmail.com>