n2kanalysis
n2kanalysis has spent eight years wiring INLA models to an S3 bucket.
A side-by-side editorial comparison of RadialMR and spatstat.geom — release velocity, themes, recent moves, and the top alternatives to consider.
| Feature | RadialMR | spatstat.geom |
|---|---|---|
| Sector | Analytics | Analytics |
| Velocity score | 0.0 | 2.5 |
| Sparks · 30d | 0 | 0 |
| Top themes | mendelian-randomization, radial-plots, correctness-audit, statistical-inference | spatial-statistics, computational-geometry, r-package, three-dimensional |
| Last editorial update | 50m ago | 4h ago |
| Website | Visit → | Visit → |
RadialMR's 2026 release corrects degrees of freedom that had been wrong since documentation.
RadialMR implements radial-plot formulations of IVW and MR-Egger Mendelian randomization, with outlier detection and interactive plotting. The recent history is thin on features and increasingly focused on the arithmetic: 1.2.4 in July 2026 fixes the degrees of freedom returned by egger_radial() to the documented n-2, corrects the heterogeneity p-value that inherited the same error, and repairs a negated lower bound in the random-effects bootstrap standard error search interval in ivw_radial().
The geometry layer under spatstat, steadily absorbing 3D patterns and missing-data semantics
spatstat.geom holds the spatial data structures and geometric operations the rest of the spatstat family builds on — windows, tessellations, images, point patterns and the operations that move between them. Recent releases split their attention between extending those structures to three dimensions and hardening the discretisation code where polygonal geometry meets a pixel grid. 3.8-2 adds more capabilities for three-dimensional point patterns.
RadialMR implements radial-plot formulations of IVW and MR-Egger Mendelian randomization, with outlier detection and interactive plotting. The recent history is thin on features and increasingly focused on the arithmetic: 1.2.4 in July 2026 fixes the degrees of freedom returned by egger_radial() to the documented n-2, corrects the heterogeneity p-value that inherited the same error, and repairs a negated lower bound in the random-effects bootstrap standard error search interval in ivw_radial().
This is a package being read closely by its maintainer rather than extended. The 1.2.x line pairs statistical corrections with defensive hardening — an rmr_format class check so unformatted input fails with a clear message, and plotly_radial() dispatching on object class instead of counting list elements. Both are the kind of change made while auditing, not while building.
Expect the audit to continue into the remaining estimator internals and print methods rather than new radial variants; the entries show no feature work queued.
spatstat.geom holds the spatial data structures and geometric operations the rest of the spatstat family builds on — windows, tessellations, images, point patterns and the operations that move between them. Recent releases split their attention between extending those structures to three dimensions and hardening the discretisation code where polygonal geometry meets a pixel grid. 3.8-2 adds more capabilities for three-dimensional point patterns.
Two threads run through this window. The first is a family-wide push into 3D that originated in the simulation package and has now reached the geometry layer. The second is a slower semantic change: 3.5-0 introduced missing or unavailable (NA) spatial objects, and 3.6-0 followed with more facilities for handling them, meaning an absent window or image became a representable value rather than an error. Around both, the plotting and discretisation code accretes steadily — nonlinear colour maps, plot backgrounds, transparency control, signed distance transforms, and repeated attention to boundary pixels.
Expect the 3D surface here to keep filling in behind the simulation package rather than leading it, given that 3.8-2 follows the 3D simulation release by two months. The entries give no indication that the NA work is finished, since it has already spanned two releases.
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 RadialMR or spatstat.geom.
n2kanalysis has spent eight years wiring INLA models to an S3 bucket.
A Fortran-descended optimizer got thread-safe, then found two flags that never worked.
ggstatsplot reached 1.0 by adding tests, having outsourced its statistics years ago.
collapse got a JSS paper and a 7x fmean speedup in the same release.
gtsummary is quietly rebuilding itself around analysis results data, one table verb at a time.
broadcast is filling in NumPy-style array broadcasting for R, operator by operator.
See all RadialMR alternatives → · See all spatstat.geom alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
Both compete on the same themes — r-package — within Analytics. spatstat.geom 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. spatstat.geom 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 RadialMR alternatives in Analytics are ranked by recent ship velocity. Browse the "RadialMR alternatives" section above for the current picks, or visit /alternatives/radialmr for the full list with editorial commentary on each.
Top spatstat.geom alternatives in Analytics are ranked by recent ship velocity. Browse the "spatstat.geom alternatives" section above for the current picks, or visit /alternatives/spatstat-geom for the full list with editorial commentary on each.