← Back to home
Comparison · Analytics

cTMed vs susier

A side-by-side editorial comparison of cTMed and susier — release velocity, themes, recent moves, and the top alternatives to consider.

Shared themes:r-package

cTMed vs susier: at a glance

FeaturecTMedsusier
SectorAnalyticsAnalytics
Velocity score2.50.0
Sparks · 30d00
Top themesmediation-analysis, continuous-time-models, r-package, statistical-methodsr-package, statistical-genetics, fine-mapping, cpp-bindings
Last editorial update3h ago1h ago
WebsiteVisit →Visit →

What is cTMed?

Continuous-time mediation effects get standardized centrality, six years into steady patch work

cTMed computes direct, indirect and total effects for continuous-time mediation models, with delta-method, Monte Carlo and bootstrap variants of each. Development is a long run of patch releases from the jeksterslab account, roughly every two months, each adding a function or two. The latest adds standardized centrality measures and allows a diagonal sigma across ten standardized estimators.

Read the full cTMed trajectory →

What is susier?

Fine-mapping workhorse susieR spends its releases hunting null-effect trimming bugs

susieR implements the Sum of Single Effects regression model for variable selection and fine-mapping, widely used in statistical genetics. The recent releases are a tight run of correctness work concentrated in one area: null effect trimming. Version 0.15.55 fixed trimming under the Servin-Stephens residual variance method, 0.15.56 fixed it again for non-uniform prior weights fourteen minutes later, 0.15.57 corrected an ELBO null space term for RSS with X and a matrix symmetry check, and 0.15.58 addressed an alpha0/beta0 issue. Version 0.16.0 migrates the C++ bindings from Rcpp to cpp11 with cpp11armadillo.

Read the full susier trajectory →

cTMed vs susier: editorial side-by-side

C
cTMed
ANALYTICS
2.5

Continuous-time mediation effects get standardized centrality, six years into steady patch work

◆ Current state

cTMed computes direct, indirect and total effects for continuous-time mediation models, with delta-method, Monte Carlo and bootstrap variants of each. Development is a long run of patch releases from the jeksterslab account, roughly every two months, each adding a function or two. The latest adds standardized centrality measures and allows a diagonal sigma across ten standardized estimators.

◆ Where it's heading

The package is filling out a matrix rather than changing shape: for each effect type there is a delta-method, a Monte Carlo and a bootstrap path, and each release closes another cell. The 2025 releases were largely externally forced — an Armadillo 15.0.x transition at CRAN, a citation addition after the Psychological Methods paper landed — which suggests the statistical core has been settled since the 1.0.6 standardization revision.

◆ Prediction

The diagonal-sigma option has now reached the standardized estimators; extending it to the remaining unstandardized variants is the obvious next cell to fill.

S
susier
ANALYTICS
0.0

Fine-mapping workhorse susieR spends its releases hunting null-effect trimming bugs

◆ Current state

susieR implements the Sum of Single Effects regression model for variable selection and fine-mapping, widely used in statistical genetics. The recent releases are a tight run of correctness work concentrated in one area: null effect trimming. Version 0.15.55 fixed trimming under the Servin-Stephens residual variance method, 0.15.56 fixed it again for non-uniform prior weights fourteen minutes later, 0.15.57 corrected an ELBO null space term for RSS with X and a matrix symmetry check, and 0.15.58 addressed an alpha0/beta0 issue. Version 0.16.0 migrates the C++ bindings from Rcpp to cpp11 with cpp11armadillo.

◆ Where it's heading

The version-number churn understates how narrow this work is — four consecutive releases touching the same trimming and residual-variance machinery suggests one area where the implementation and the intended behavior had drifted apart. The 0.16.0 binding migration is the only structural change, and it is invisible to users while mattering for build portability and long-term maintenance. Development is clearly active, with automated release tooling and dependency bumps flowing through the same stream.

◆ Prediction

With the binding migration just landed, near-term releases are likely to address fallout from it alongside continued fixes in the same trimming and residual-variance code.

Alternatives to cTMed and susier

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 cTMed or susier.

See all cTMed alternatives → · See all susier alternatives →

Recent activity from cTMed and susier

Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.

  1. 27d agocTMedStandardized centrality measures and diagonal-sigma support
  2. 3mo agosusierMigrates C++ bindings from Rcpp to cpp11 and cpp11armadillo
  3. 3mo agosusierFixes alpha0/beta0 handling under Servin-Stephens
  4. 4mo agosusierCorrects the null space ELBO term for RSS with X
  5. 5mo agosusierFixes null effect trimming with non-uniform prior weights
  6. 5mo agosusierFixes null effect trimming under Servin-Stephens estimation
  7. 6mo agocTMedMinor method edits
  8. 10mo agocTMedPackage citation added for the Psychological Methods paper
  9. 10mo agocTMedArmadillo 15.0.x compatibility for CRAN
  10. 1y agocTMedStandardization reworked around the steady-state covariance matrix
  11. 1y agocTMedBootstrap centrality estimators and MCPhiSigma()

Frequently asked questions

What is the difference between cTMed and susier?

Both compete on the same themes — r-package — within Analytics. cTMed 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.

Is cTMed better than susier?

Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. cTMed 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.

What are the best alternatives to cTMed?

Top cTMed alternatives in Analytics are ranked by recent ship velocity. Browse the "cTMed alternatives" section above for the current picks, or visit /alternatives/ctmed for the full list with editorial commentary on each.

What are the best alternatives to susier?

Top susier alternatives in Analytics are ranked by recent ship velocity. Browse the "susier alternatives" section above for the current picks, or visit /alternatives/susier for the full list with editorial commentary on each.