STACAS
Single-cell batch correction that learned to use cell labels, then spent three releases chasing Seurat.
A side-by-side editorial comparison of fitVARMxID and kde1d — release velocity, themes, recent moves, and the top alternatives to consider.
A VAR-model fitting package acquiring the standard R methods it launched without
fitVARMxID fits vector autoregressive models via OpenMx identification, and is one of several packages maintained by the jeksterslab account. Its recent releases are small and additive: confint() and plot() methods, a save function, and before that a documentation pass. The feed also carries automated build commits that are pure CI artifacts.
A univariate density estimator that added zero-inflated data and reopened its C++ API to do it.
kde1d estimates univariate densities with local polynomial kernel methods, handling bounded, discrete and now zero-inflated variables through a single type argument, with the numerical work in a header-only C++ library usable outside R. Version 1.1.0 added the zero-inflated discrete-continuous mixture case and shipped a new C++ API as an explicit breaking change; 1.1.1 followed in June with auto-generated notes and no description.
fitVARMxID fits vector autoregressive models via OpenMx identification, and is one of several packages maintained by the jeksterslab account. Its recent releases are small and additive: confint() and plot() methods, a save function, and before that a documentation pass. The feed also carries automated build commits that are pure CI artifacts.
This is a package settling into R conventions rather than growing capability. Adding confint() and plot() is the standard-methods work most modeling packages do once the estimation core is stable — it signals the author considers the fitting side done. Cadence is roughly quarterly and the changes get smaller each time.
Further method coverage — summary(), predict(), or coef() — is the likely next step, since confint() and plot() are usually the first two of that set rather than the last.
kde1d estimates univariate densities with local polynomial kernel methods, handling bounded, discrete and now zero-inflated variables through a single type argument, with the numerical work in a header-only C++ library usable outside R. Version 1.1.0 added the zero-inflated discrete-continuous mixture case and shipped a new C++ API as an explicit breaking change; 1.1.1 followed in June with auto-generated notes and no description.
The package has alternated between performance work and widening the class of data it accepts. The 1.0.0 release was the performance milestone — FFT-based estimation, a better integration algorithm for the p, q and r functions, deterministic jittering replacing randomness, and standalone C++ headers. The 1.1.0 release is the scope milestone, adding a third data type to the two it already handled. Releases come from the same maintainer as svines and cluster on shared dates, so changes in the underlying C++ surface across the vine and density stack tend to ship together.
With the C++ API deliberately reworked for standalone use at 1.1.0, further work most plausibly consolidates that interface rather than adding data types. What 1.1.1 actually changed is not readable from its body.
Other Analytics 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 fitVARMxID or kde1d.
Single-cell batch correction that learned to use cell labels, then spent three releases chasing Seurat.
A debugger for ggplot2's internals, hardening its grip as the internals it traces keep moving.
Stationary vine copulas for time series, released in lockstep with the rest of Nagler's vine stack.
A single-purpose ggplot2 extension that has spent six years tracking ggplot2 instead of growing.
A Star Trek data package that became a Memory Alpha web client and has been patching scrapers ever since.
A thin EIA energy-data client whose whole story is making bulk queries survive the API's limits.
See all fitVARMxID alternatives → · See all kde1d alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
Both compete on the same themes — r-package — within Analytics. fitVARMxID is currently shipping more aggressively (velocity 2.5 vs 0.0), with 0 editorial sparks in the last 30 days against 0. 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. fitVARMxID is currently shipping more aggressively (velocity 2.5 vs 0.0), with 0 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other Analytics products to evaluate alongside.
Top fitVARMxID alternatives in Analytics are ranked by recent ship velocity. Browse the "fitVARMxID alternatives" section above for the current picks, or visit /alternatives/fitvarmxid for the full list with editorial commentary on each.
Top kde1d alternatives in Analytics are ranked by recent ship velocity. Browse the "kde1d alternatives" section above for the current picks, or visit /alternatives/kde1d for the full list with editorial commentary on each.