RBesT-package: R Bayesian Evidence Synthesis Tools

In RBesT: R Bayesian Evidence Synthesis Tools

R Bayesian Evidence Synthesis Tools

Description

The RBesT tools are designed to support in the derivation of parametric informative priors, asses design characeristics and perform analyses. Supported endpoints include normal, binary and Poisson.

Details

For introductory material, please refer to the vignettes which include

• Introduction (binary)

• Introduction (normal)

• Customizing RBesT Plots

• Robust MAP, advanced usage

The main function of the package is gMAP(). See it's help page for a detailed description of the statistical model.

Global Options

Option	Default	Description
RBesT.MC.warmup	2000	MCMC warmup iterations
RBesT.MC.iter	6000	total MCMC iterations
RBesT.MC.chains	4	MCMC chains
RBesT.MC.thin	4	MCMC thinning
RBesT.MC.save_warmup	FALSE	MCMC warmup samples saving
RBesT.MC.control	⁠list(adapt_delta=0.95,⁠	sets control argument for Stan call.
	⁠stepsize=0.01,⁠	adapt_delta defaults to 0.99 whenever
	⁠max_treedepth=20)⁠	RBesT.MC.s2z is FALSE
RBesT.MC.s2z	TRUE	sum-to-zero parametrization of the group
		random effects; FALSE uses the conventional representation;
		see the references
RBesT.MC.ncp	3	group-effect parametrization: 0=CP, 1=NCP,
		2=automatic CP/NCP endpoint from quadrature-derived
		per-group fractions, 3=automatic partial centering
RBesT.MC.init	1	range of initial uniform [-1,1] is the default
RBesT.MC.rescale	TRUE	Automatic rescaling of raw parameters
RBesT.verbose	FALSE	requests outputs to be more verbose
RBesT.integrate_args	⁠list(lower=-Inf,⁠	arguments passed to integrate for
	⁠upper=Inf,⁠	adaptive integration of densities (used when
	⁠rel.tol=.Machine$double.eps^0.25,⁠	RBesT.integrate_method is "adaptive"
	⁠abs.tol=.Machine$double.eps^0.25,⁠	or for non-normMix densities)
	⁠subdivisions=1E3)⁠
RBesT.integrate_prob_eps	1E-6	probability mass left out from tails if integration needs to be restricted in range
RBesT.integrate_method	"GQ"	integration method for mixture densities: "GQ" (Gaussian quadrature, deterministic) or "adaptive" (adaptive Gauss-Kronrod). GQ uses Gauss-Hermite for normMix, Gauss-Jacobi for betaMix, and Gauss-Laguerre for gammaMix.
RBesT.GQ_nodes	20	starting number of Gaussian quadrature nodes (only used when RBesT.integrate_method is "GQ")
RBesT.GQ_rel_tol	1E-4	relative tolerance target for GQ refinement; the node count is increased until successive estimates agree within ⁠max(RBesT.GQ_abs_tol, RBesT.GQ_rel_tol * |I|)⁠. Set to a non-finite or non-positive value (e.g. Inf) to disable refinement (single evaluation at RBesT.GQ_nodes).
RBesT.GQ_abs_tol	1E-6	absolute tolerance floor for GQ refinement
RBesT.GQ_max_nodes	240	upper cap on the GQ node count during refinement
RBesT.GQ_node_growth	2	multiplicative growth factor for the GQ node count between refinement steps
RBesT.GQ_on_nonconvergence	"adaptive"	behaviour when GQ refinement reaches RBesT.GQ_max_nodes without meeting tolerance: "adaptive" (fall through to adaptive integration), "warn" (warn and return best estimate), "error", or "silent"
RBesT.decision2S_boundary	"adaptive"	tracing scheme for the decision boundary in decision2S_boundary() (and hence oc2S/pos2S): "adaptive" (recursive subdivision of the y2 range with early stop where the boundary is linear for the normal case, and monotone constant-run filling for the binomial/Poisson cases) or "grid" (legacy exhaustive/uniform sweep). Boundary values are unchanged (identical for the discrete families, within solver tolerance for the normal case); "adaptive" needs far fewer root solves.

Version History

See NEWS.md file.

Author(s)

Maintainer: Sebastian Weber [e-mail]

Authors:

• Sebastian Weber [e-mail]

Other contributors:

• Novartis Pharma AG [copyright holder]

• Beat Neuenschwander [e-mail] [contributor]

• Heinz Schmidli [e-mail] [contributor]

• Baldur Magnusson [e-mail] [contributor]

• Yue Li [e-mail] [contributor]

• Satrajit Roychoudhury [e-mail] [contributor]

• Lukas A. Widmer [e-mail] (ORCID) [contributor]

• Daniel Sabanés Bové [e-mail] (ORCID) [contributor]

• Trustees of Columbia University (R/stanmodels.R, configure, configure.win) [copyright holder]

References

\insertRef

rstanRBesT

\insertRef

pinkney2026RBesT

See Also

Useful links:

• https://opensource.nibr.com/RBesT/

• Report bugs at https://github.com/Novartis/RBesT/issues

RBesT documentation built on Sept. 18, 2026, 5:06 p.m.