mice
mice can finally predict, not just estimate, from multiply imputed data.
A side-by-side editorial comparison of formr and midr — release velocity, themes, recent moves, and the top alternatives to consider.
formr's R client reached CRAN and moved its recommended path to the v1 REST API.
formr is the R-side client for formr.org, the open study framework used to run longitudinal and experience-sampling questionnaires. In May it reached CRAN for the first time, released in step with formr.org server v1.0.0, and the formr_api_* family built on the server's RESTful surface became the supported entry point. The three releases since have been repair work on the paths that move rendered output and API results.
A black-box interpreter reaches CRAN, then learns multi-class and survival responses
midr explains black-box models by fitting an interpretable surrogate through Maximum Interpretation Decomposition — main effects plus second-order interactions, with exact Shapley values for the surrogate. Two months after its first CRAN release it can take a matrix response, which covers multi-class classification and survival models, and hold collections of fitted interpretations in midlist and midrib objects for comparison.
formr is the R-side client for formr.org, the open study framework used to run longitudinal and experience-sampling questionnaires. In May it reached CRAN for the first time, released in step with formr.org server v1.0.0, and the formr_api_* family built on the server's RESTful surface became the supported entry point. The three releases since have been repair work on the paths that move rendered output and API results.
The direction is consolidation around the v1 API while the legacy Classic path is left running but demoted in the vignette. The complication is that CRAN's requirements and the OpenCPU server's requirements pull against each other: CRAN review pushed rendering into tempdir() with random filenames, which broke rforms.org because the server fetches a fixed knit.html, and 1.1.2 had to put it back. The 1.2.0 note describes the same write-directory problem being solved in an OpenCPU-aware way rather than reverted, alongside making dependencies installable under WASM.
Two of the last three releases were regressions in the render path, so the OpenCPU-aware write directory in 1.2.0 is the change most likely to need follow-up. The Classic formr_results() path remains in the package with no removal date announced, and nothing in these entries indicates when that ends.
midr explains black-box models by fitting an interpretable surrogate through Maximum Interpretation Decomposition — main effects plus second-order interactions, with exact Shapley values for the surrogate. Two months after its first CRAN release it can take a matrix response, which covers multi-class classification and survival models, and hold collections of fitted interpretations in midlist and midrib objects for comparison.
The releases move outward along two axes at once: what can be interpreted, and how much of it fits in memory. Version 0.5.3 rebuilt the fitting path to avoid materialising large design matrices and added a save.memory option; 0.6.0 widened the response from a vector to a matrix and added parametric link functions. Class and argument names were shortened in the same release, so the package is still willing to break itself this early.
With multiple models now held in one object and visualisation methods for them, comparison across models is the surface most likely to fill out next — the collection classes exist but the notes describe manipulation and plotting rather than any comparison metric.
Other Infra & APIs products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either formr or midr.
mice can finally predict, not just estimate, from multiply imputed data.
A market-microstructure toolkit that keeps adding estimators as the papers land.
A vowel-analysis package trimming dependencies after an email address got it archived.
The R half of the EMU speech database system, fixing what was quietly broken.
A Bayesian model-averaging package spending its 2.0 on memory, not methods.
tidyplots keeps rebuilding its own foundations rather than layering around them.
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
They serve adjacent needs but don't currently overlap on shipped themes. formr and midr are shipping at a similar cadence (velocity 0.0 vs 0.0, both within Sparkpulse's "active" band). See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. formr and midr are shipping at a similar cadence (velocity 0.0 vs 0.0, both within Sparkpulse's "active" band). For your specific use case, the alternatives sections above list other Infra & APIs products to evaluate alongside.
Top formr alternatives in Infra & APIs are ranked by recent ship velocity. Browse the "formr alternatives" section above for the current picks, or visit /alternatives/formr for the full list with editorial commentary on each.
Top midr alternatives in Infra & APIs are ranked by recent ship velocity. Browse the "midr alternatives" section above for the current picks, or visit /alternatives/midr for the full list with editorial commentary on each.