LoginSign Up
← Back to all sparks
P

parameters

ANALYTICS
Velocity0.0

Extract, compute and explain the parameters of statistical models in R

github.com/easystats/parameters ↗

easystats' parameters package absorbs one more model class every few weeks

easystatsmodel-parametersstandardizationmixed-modelsstatistical-outputr-package
◆Current state
parameters extracts and formats coefficients from an enormous range of R model objects, and its releases read as a running ledger of that range expanding — lavaan and lavaan.mi, survey, lcmm, glmmTMB, fixest, marginaleffects, ordinal. Recent versions ship roughly monthly with a mix of new support, new arguments, and fixes for label handling and standard errors. The most consequential recent change is behavioral: post-hoc standardization no longer standardizes the intercept, setting it and its inferential statistics to NA.
◆Where it's heading
The package's job is to be the universal adapter for model output, so its roadmap is effectively set by what the R modelling ecosystem produces. Two threads are visible beyond coverage: getting standard errors right for awkward cases such as frailty terms and robust vcov matrices, and getting labels right when factors are converted on the fly or character variables appear in a formula. Interoperability inside easystats keeps tightening, with equivalence_test() gaining methods for modelbased objects.
◆Prediction
Given the cadence, the next release will most likely add another model class alongside label and standard-error fixes rather than change how the package works.

◆Recent moves

  1. 1mo ago

    parameters 0.29.2 extends lavaan support and fixes label dropping

    simulate_model(), simulate_parameters(), and equivalence_test() start working for lavaan objects, factor_analysis() and principal_components() gain format() methods, and label handling is fixed for character variables and on-the-fly factor conversions. The label fixes matter because a silently dropped label is a wrong table nobody notices.

    View source ↗
  2. 2mo ago

    parameters 0.29.1 adds a cluster argument and fixes vcov handling

    bootstrap_model() gains a cluster argument for snow-based parallelism, and vcov handling is fixed for dpoMatrix objects and glmmTMB models. Narrow work on the robust standard-error path.

    View source ↗
  3. 3mo ago

    parameters 0.29.0 stops standardizing the intercept in post-hoc methods

    Post-hoc standardization no longer standardizes the intercept, instead setting it and all its inferential statistics to NA, plus lavaan.mi support and faster model_parameters() for large mgcv GAMs with random effects. A deliberate correctness change that will alter existing output.

    View source ↗
  4. 8mo ago

    parameters 0.28.3 adds Kenward-Roger and Satterthwaite for glmmTMB

    Adds support for survey and lcmm objects, equivalence_test() methods for modelbased objects, Kenward-Roger and Satterthwaite ci_method options for glmmTMB, and a fixest standardization fix. The glmmTMB degrees-of-freedom methods are the substantive part for mixed-model users.

    View source ↗
  5. 11mo ago

    parameters 0.28.2 updates tests for the latest fixest release

    Test updates to resolve issues with the latest fixest release. Upstream compatibility only.

    View source ↗
  6. 11mo ago

    parameters 0.28.1 adds robust standard errors for glmmTMB

    glmmTMB methods gain vcov support for robust standard errors, Bayesian detection improves for marginaleffects objects, and the code base adapts to marginaleffects 0.29.0. Continuous adaptation to a fast-moving dependency.

    View source ↗