LoginSign Up
← Back to all sparks
R

rbmi

ANALYTICS
Velocity2.5

Reference based multiple imputation R package. Contribute to openpharma/rbmi development by creating an account on GitHub.

github.com/openpharma/rbmi ↗

Reference-based multiple imputation for trials, now shipping without Bayesian support by default.

clinical-trialsmissing-datamultiple-imputationpharmaverseestimandsr-package
◆Current state
rbmi implements reference-based multiple imputation for longitudinal clinical trial data with missing values — the estimand machinery regulators expect for handling intercurrent events and dropout. The consequential recent change was 1.3.0 moving rstan from a hard dependency to Suggests, which takes Bayesian imputation out of the default install. Since then the work has been documentation and nomenclature discipline: 1.6.1 standardized on MNAR over a mixed NMAR/MNAR vocabulary and deprecated the nmar.rm argument accordingly.
◆Where it's heading
The package is optimizing for adoption friction over feature breadth. Dropping a compiled Stan dependency from the default install, deprecating a bespoke seed argument in favor of base set.seed(), and aligning lsmeans() behavior and weight naming with emmeans all point the same direction — behave like a conventional R package rather than a specialized one. Documentation work in 1.6.1 covering @return on every exported function and executable examples reads as preparation for validation scrutiny rather than user demand.
◆Prediction
Given the FAQ vignette's validation statement and the recent documentation completeness pass, the next work is more likely qualification and estimand documentation than new imputation methods.

◆Recent moves

  1. 22d ago

    MNAR nomenclature standardized, documentation completed

    Adopts the lifecycle package, documents @return on all exported functions, adds executable examples where they were missing, and settles on MNAR throughout — deprecating longdata$get_data's nmar.rm in favor of mnar.rm. Nothing changes in what the imputation methods compute.

    View source ↗
  2. 1y ago

    rstan demoted to Suggests, Bayesian imputation now opt-in

    ⚡ SPARK

    The break in the package's history: rstan becomes a suggested dependency, so Bayesian imputation is absent from a default install until users add rstan themselves. Paired with a seed argument deprecation and an lsmeans() weights rename that changes which weights a given call uses.

    View source ↗
  3. 2y ago

    rbmi v1.2.5

    A minimal release addressing CRAN check NOTEs with no user-facing changes.

    View source ↗