All Classes and Interfaces
Class
Description
Estimate and independent left/right convergence evidence for E[|X|^p].
Device-resident batched logistic-regression posterior with a spherical normal prior.
Warmup-only candidate-specific Gaussian birth adaptation with checkpointable moments.
Rebuilds and draws a caller-certified log-concave full conditional.
Adaptive tangent-envelope rejection sampler for a caller-certified
differentiable log-concave density on finite support.
Per-model isotropic random walk with warmup-only Robbins-Monro scale adaptation.
Coordinated many-chain static HMC with ChEES or SNAPER trajectory adaptation.
Controls coordinated ChEES/SNAPER trajectory-length adaptation across chains.
Draws plus the shared trajectory adaptation selected by ChEES or SNAPER.
Automatic adjusted-MCLMC pilot search for integrator step and decorrelation length.
Pilot-search controls for adjusted MCLMC step size and decorrelation length.
Final adjusted-MCLMC chain and auditable pilot objective values.
Metropolis-adjusted microcanonical Langevin sampler (MHMCHMC).
Spectral, distortion/Choquet, and entropic risk measures.
Finite-difference Newton solver for small and medium dense algebraic systems.
Solver controls.
Converged root and diagnostic counts.
Residual function
F(state, parameters, data) = 0.Ansari-Bradley test statistic
Create an approximation function.
Types of approximation
Bounded Arcsine distribution; bounded by [a, b].
Three-parameter asymmetric Laplace distribution used in quantile regression.
A scalar distribution that can report probability mass at an exact point.
Exact gradient-informed Barker proposal with symmetric Gaussian magnitudes.
Optional accelerator-facing contract for evaluating independent states in one call.
Compiled named model evaluated on an unconstrained state space.
Bivariate BB1 (Clayton-Gumbel) copula, theta >= 0 and delta >= 1.
Collection of Bessel functions.
Beta binomial distribution, taken from gamlss.dist package, plus some underflow guard.
Beta-negative-binomial distribution using the extraDistr parameterization.
Beta-prime (beta of the second kind) distribution.
Selects the BTPE acceptance test used for binomial random generation.
Birnbaum-Saunders (fatigue-life) distribution with shape
alpha,
scale beta, and location mu.Gumbel's type-I bivariate logistic distribution as used by VGAM.
Bivariate Poisson distribution formed from three independent Poisson counts.
Translation of the infamous Bobyqa algorithm by Michael J.
Three-state boolean: TRUE, FALSE, NA
Immutable wall-clock cost profile for integrand callback evaluations.
Finite categorical distribution over numeric outcomes.
Immutable settings for an adaptive monotone numerical CDF table.
Winsorized/censored scalar distribution with explicit atoms at both bounds.
Immutable truncation settings for certified infinite discrete supports.
Finite approximation to an infinite integer-supported distribution, stopped
only when user-provided tail certificates bound the omitted probability.
CGMY/KoBoL infinitely-divisible return law in (C,G,M,Y,location) form.
In-memory state-and-stream restart point including a cloned random engine.
Versioned JSON and tidy CSV interchange for retained chain draws.
Immutable retained samples, sampler statistics, adaptation and restart state.
Deterministic multi-chain execution and checkpoint continuation helpers.
Chart-neutral immutable dataset suitable for SVG, JSON, CSV, or UI adapters.
Checksummed, versioned binary checkpoint envelope with compatibility fingerprints.
Immutable lower Cholesky factor with reusable SPD solves.
Selected-coordinate streaming sink with independently compressed, recoverable chunks.
Exchangeable Clayton copula with nonnegative dependence.
Selected-coordinate columns read from a chunked draw store.
Compiled model plus deterministic or random generated-quantity program.
Immutable double-precision complex value used by Java integrations.
Gaussian Metropolis sweeps with independently adapted coordinate scales.
Selects automatic, CPU, or required accelerator execution.
Concrete compute API or native library family.
A differentiable target whose numerical evaluation is bound to a compute backend.
Optional backend for vector, dense-linear-algebra, and batched likelihood work.
Discovers optional accelerator providers without making them core dependencies.
Immutable compute-device capabilities relevant to statistical kernels.
Immutable backend, runtime, driver, and device provenance.
Controls whether NUTS target evaluation may or must use an accelerator.
Selected compute backend, device provenance, and ownership for one workflow.
Exact scalar law conditional on lower < X <= upper.
Class defining constants.
Standard parameter constraints and their Jacobian-aware transforms.
Determines which advisory findings prevent analyzed construction.
Gaussian random-walk update of a continuous block conditional on all other coordinates.
Unit-Jacobian birth/death mapping that inserts or removes one parameter coordinate.
Split/merge map x,u to x+u,x-u with forward log-Jacobian log(2).
Typed support for one coordinate in a mixed continuous/discrete state.
A copula on the unit hypercube.
Immutable classification of a proposed copula evaluation point.
Location of the point relative to the unit hypercube.
Joint distribution composed from a copula and continuous univariate
marginals.
Built-in families supported by dependence fitting and selection.
Controls rank-based initialization and optional likelihood refinement.
Result of fitting one copula family to pseudo-observations.
Rank transformation and dependence fitting for the built-in copula families.
Row-level log-density and unit-cube boundary diagnostics for a copula model.
Auditable likelihood aggregation for continuous, discrete, or mixed data.
A scalar marginal together with its continuity/atom contract.
Measure used by a joint likelihood contribution.
Numerical controls for mixed continuous/discrete copula likelihoods.
Joint density, mass, or mixed-measure likelihood contribution.
Information criterion used by automatic copula-family selection.
Ranked family fits and the selected successful candidate.
Fits candidate families and ranks them by AIC or BIC.
Tail dependence, finite-level concentration, and bivariate stress regions.
Deterministic CPU reference implementation for every accelerated primitive.
Immutable one-based compressed-row sparse matrix compatible with Stan CSR arrays.
Simplified C-vine copula assembled from bivariate conditional copulas.
Implicit-Euler solver for index-1 differential-algebraic systems.
Differential-algebraic residual
F(t, y, y') = 0.Delaporte count: Poisson(lambda) plus NB(shape, successProbability).
Corresponds to R's density function.
One evidence-based finding produced by a numerical distribution analyzer.
Factories for trace, rank, autocorrelation, energy, and pair-plot datasets.
Dependency-free RFC 8259 serialization for numerical diagnostic reports.
Balanced starting points for custom-kernel diagnostics.
A log density capable of adding its gradient to caller-owned storage.
A factor that adds derivatives with respect to all constrained coordinates.
One side of a dimension-matching map: state plus complementary auxiliaries.
Reversible mapping between parameter/auxiliary pairs of equal total dimension.
Executable round-trip, dimension, and reciprocal-Jacobian validation for RJ maps.
Dirichlet distribution on a probability simplex.
Dirichlet-multinomial (multivariate Pólya) distribution.
FDR procedures that exploit known heterogeneous discrete null CDFs.
Rejection decisions and level-dependent DBH critical values.
Discrete Laplace distribution on the lattice
location + Z.Symmetric Metropolis update for one bounded or unbounded discrete coordinate.
Finite null distribution of a discrete p-value.
User-supplied certificate bounding all unnormalized mass beginning at an
omitted integer.
Factory methods for common caller-certified infinite-series tail bounds.
Nakagawa-Osaki type-I discrete Weibull distribution on nonnegative integers.
Reproducible aggregation, product/ratio, compound-sum, and scenario helpers.
Numerical self-consistency checks for a constructed distribution.
An approximate composed law together with strategy, error, and seed provenance.
Bounded MLE/MAP fitting with censored and interval observations.
Concise factories for composing scalar distribution objects.
Comparing two distributions
Numerical transform, cumulant, Fourier-inversion, and Esscher-tilt helpers.
Result retaining the tilted law and its normalization diagnostics.
Location and energy error for one divergent retained transition.
Extracts sampler pathologies with coordinates suitable for plotting.
Streaming destination for retained draws; implementations must copy if needed later.
Simplified D-vine copula assembled from bivariate conditional copulas.
Tuning-free elliptical slice sampler; target is the likelihood-only log density.
Discrete empirical distribution that samples observations with replacement.
Immutable equal-weight empirical distribution used by reproducible fallbacks.
Thread-confined log-density wrapper reporting value and gradient work.
How an inspected operation is expected to execute.
Immutable prediction of where and how one operation will execute.
Distribution of an independent normal variate plus an exponential variate.
Immutable name-to-Java registry for forward-declared Stan functions.
Immutable external-function values and derivatives with respect to flattened arguments.
Extreme distribution.
GEV/GPD fitting, tail-index estimators, return levels, and threshold diagnostics.
Immutable factor timing and numerical-stability snapshot.
Wraps factors without changing whether analytic gradients are available.
Immutable factor metadata and evaluator.
Five-parameter Feller-Pareto distribution from actuar.
Atom-aware tail-risk, partial-moment, and option-payoff functionals.
Exact full-conditional update for one finite integer or categorical coordinate.
Immutable equally-spaced finite distribution used by exact/FFT/Panjer grids.
First-class inference result combining chains, diagnostics, and provenance.
Adapts one frozen ordinary JDistlib sampler transition for use within an RJ model.
Immutable FP32 lower Cholesky factor with reusable SPD solves.
Immutable FP32 CSR matrix with one-based Stan-compatible indices.
Immutable FP32 partial-pivoted LU factorization of a square matrix.
Immutable FP32 column-pivoted Householder QR factorization.
Immutable FP32 thin singular-value decomposition
A = U*S*Vt.Immutable FP32 sparse Cholesky factor with reusable solves.
Immutable FP32 eigendecomposition of a real symmetric matrix.
FP32 pivoted
P*A*P' = L*D*L' factorization with 1x1/2x2 D blocks.VGAM folded normal distribution, including asymmetric positive and negative
scaling factors
a1 and a2.Work, truncation, and convergence controls for adaptive Fourier inversion.
Exchangeable Frank copula.
Fretchet distribution.
Evidence gathered while probing and repeatedly integrating a kernel.
Immutable settings for probability-kernel sanity analysis.
Gaussian copula parameterized by a positive-definite correlation matrix.
Gaussian prior/reference measure used by elliptical slice and pCN updates.
Candidate-specific or common Gaussian birth proposal.
Independent Gaussian sparse-coefficient birth proposal.
Four-parameter generalized beta distribution of the second kind (GB2).
Prentice generalized-F survival distribution used by flexsurv.
Stacy generalized gamma distribution as parameterized by VGAM.
Generalized-hyperbolic law in the canonical (lambda, alpha, beta, delta, mu)
parameterization, with alpha > |beta| and delta > 0.
Generalized-inverse-Gaussian law in (lambda, chi, psi), chi/psi positive.
Generalized Pareto Distribution
Taken from EVD package of R
Contract implemented by ahead-of-time generated script wrappers.
Named scalar generated from one retained unconstrained state.
Appends generated quantities to each state before forwarding it to another sink.
An interface for a generic distribution.
Coordinate associated with divergences and a scale/reparameterization suggestion.
Ranks coordinates whose divergent and non-divergent locations are most separated.
Generalized extreme value distribution.
One exact or MCMC-within-Gibbs state update.
Composes exact, adaptive-rejection, Metropolis, or blocked Gibbs kernels.
Gompertz distribution with shape and rate parameters.
Immutable comparison between supplied and finite-difference gradients.
Reports whether a differentiable target uses analytic rather than fallback gradients.
Finite-difference adapters and gradient validation utilities.
Gumbel distribution.
Exchangeable Gumbel copula.
Half-Cauchy distribution with positive scale
sigma.Half-normal distribution, the distribution of the absolute value of a
zero-centered normal variate with scale
sigma.Half-Student-t distribution with degrees of freedom and scale.
Fixed-trajectory HMC with dual-averaged step size and covariance adaptation.
Diagnostic code, quantitative evidence, and an actionable remediation.
Machine-readable inference health severity.
Projected velocity-Verlet solver for holonomic index-3 mechanical DAEs.
Position/velocity trajectory and maximum observed constraint residual.
Mechanical index-3 DAE described by acceleration and holonomic constraints.
Huber least-favourable distribution with Gaussian center and exponential tails.
Hurdle negative binomial with
pi denoting positive-count mass.Hurdle Poisson with
pi denoting the probability of being positive.One support-aware transition in a scheduled hybrid sampler.
Outcome of one hybrid-kernel update.
Scheduled support-aware sampler for fixed-dimensional mixed continuous/discrete targets.
Per-kernel acceptance and support diagnostics for a hybrid schedule.
Retained mixed-state chain and diagnostics from its scheduled kernels.
Immutable modern integration result.
Checked implied-volatility inversion result.
Product copula representing mutual independence.
Concise facade for reproducible multi-chain fitting.
Parses reusable compute switches for command-line applications embedding JDistlib.
Dependency-free JSON, tidy CSV, and SVG adapters for chart-neutral data.
Actionable policy over sampler and posterior diagnostics.
Self-contained headless HTML report composed from diagnostic data and SVGs.
Deterministic validation, constrained initialization, and bounded retry helpers.
Adaptive numerical integration corresponding to R 4.6.1
stats::integrate.Dependency-free JSON serialization for integration diagnostics.
Immutable options for hardened numerical integration.
Builder for
IntegrationOptions.Where opt-in hardened callback evaluations execute.
Available integration strategies.
Results from repeating an integral under stricter and differently split settings.
Stable, typed interpretation of legacy QUADPACK-compatible status codes.
Inverse normal (or Wald) distribution.
Per-iteration sampler statistics used by convergence diagnostics.
Bivariate Joe copula with upper-tail dependence and theta >= 1.
Kendall tau distribution
Immutable result of one reusable Markov transition.
Kumaraswamy distribution
Laplace distribution, from VGAM package
Small deterministic L-BFGS maximizer intended for initialization and MAP fits.
Time-scaled increment of an infinitely-divisible transform-defined unit law.
One-parameter Lindley lifetime distribution.
Backend-neutral FP64 BLAS, sparse-BLAS, and reusable factorization surface.
Backend-neutral operation identifiers used for capability and routing inspection.
Routines that I took from LINPACK library.
Closeable generated-model factory and its isolated class loader.
An unnormalized log density on an unconstrained Euclidean state space.
Batched logistic-regression log densities and gradients.
Logit-normal distribution on the open unit interval.
Log logistic distribution.
Pointwise, paired comparison of models evaluated with PSIS-LOO.
Stateful LORD++ online-FDR controller for a prespecified hypothesis order.
Immutable FP64 partial-pivoted LU factorization of a square matrix.
Makeham survival distribution with scale, shape, and constant hazard.
Deterministic many-short-chain execution using common-initialization superchains.
Results and nested convergence diagnostics from a superchain design.
Fixed-capacity selected-coordinate draw sink and zero-copy memory-mapped reader.
Whether a triangular matrix stores or implies its diagonal.
Side on which a triangular matrix operates.
Transposition applied to a row-major dense matrix operand.
Stored triangle of a triangular matrix.
Maxwell distribution using VGAM's positive rate parameterization.
Maxwell-Boltzmann speed distribution using the conventional scale
sigma, the common standard deviation of three independent centered
normal coordinates.Immutable parameter and sampler diagnostics with machine-readable output.
Rank-normalized R-hat, bulk/tail ESS, MCSE, and sampler diagnostics.
Dependency-free versioned JSON serialization for inference diagnostics.
Meixner return law in the (scale, skew, shape, location) parameterization.
MersenneTwister and MersenneTwisterFast
MersenneTwister and MersenneTwisterFast
Immutable Euclidean metric selection for HMC-family samplers.
Metropolis-adjusted Langevin sampler with dual-averaged proposal scale.
Gaussian random-walk update for a declared continuous or discrete state block.
Joint distribution with continuous, discrete, or mixed scalar marginals.
Coordinate-by-coordinate support declaration for hybrid MCMC.
Normalized finite mixture of scalar distribution objects.
Fluent builder for named constrained parameters and model factors.
Validated on-disk compilation cache for generated model wrappers.
Immutable named numeric data supplied to a model.
Cached per-factor values for proposal algorithms that change few coordinates.
Non-thread-safe allocation-free evaluator intended for one sampler chain.
One prior, likelihood, or constraint contribution to a model log density.
Analytic common priors and likelihood factors for the programmatic builder.
Immutable bipartite parameter/factor graph for inspection and rendering.
Graphviz DOT and versioned JSON export for model dependency graphs.
Java-native compiler for the JDistlib language and its Stan-compatible source core.
Minimal ahead-of-time source-generation CLI for Gradle and shell workflows.
Parse, validation, or compilation failure with source diagnostics.
Ahead-of-time Java source generation for a validated embedded model script.
Dispatches to a distinct within-model kernel for each declared model identifier.
Read-only named view of one constrained model state and its observed data.
Immutable settings for absolute-moment diagnostics.
Builder for moment orders and the left/right reporting boundary.
Distribution induced by a differentiable, strictly monotone transformation.
MCSE and efficiency helpers for one stationary retained sequence.
Multinomial mass and random generation for a vector of category counts.
Multiple-testing adjustments and Storey q-values.
Result of the level-dependent two-stage BKY procedure.
Result for a family whose unrecorded p-values are known to exceed a limit.
Result of the two-level Benjamini-Bogomolov grouped procedure.
Supported p-value adjustment procedures.
Result of a level-dependent step-down FDR procedure.
Abstraction of a function with multiple parameters
Multivariate Cauchy distribution, the multivariate Student t law with one df.
Multivariate GH/NIG/VG, symmetric stable, or normal-tempered-stable construction.
Sampling without replacement from multiple population categories.
Symmetric multivariate Laplace law defined as a normal-exponential mixture.
Component-wise exponential transform of a multivariate normal vector.
Multivariate normal density and random generation using a covariance matrix.
Elliptical multivariate power-exponential (generalized Gaussian) law.
Accuracy and work limits for randomized multivariate probability integration.
Result of a numerical multivariate probability calculation.
Terminal status of a numerical multivariate probability calculation.
Elliptical multivariate Student t distribution.
Number of draws needed to observe
r white balls without replacement.Manually translated from R's Distlib by Roby Joehanes
Named NIG specialization of the generalized-hyperbolic family.
A package about normality testing.
Normal-tempered-stable law defined by a tempered-stable normal variance mixture.
Multinomial-candidate NUTS with windowed adaptation and configurable metrics.
Reusable monotone CDF approximation built from directly integrated values.
A continuous distribution obtained by numerically normalizing a nonnegative
kernel over a real interval.
Fluent construction with optional analysis and sampling configuration.
A finite discrete distribution obtained by normalizing a nonnegative weight
function over a declared set of numeric outcomes.
Self-consistency and moment diagnostics for numerical distributions.
Analysis plus the result of attempting to construct a numerical distribution.
Immutable diagnostics for an approximate scalar calculation.
Numerical distribution over a union of continuous intervals and optional
point atoms.
Immutable union of continuous intervals, optional atoms, and singularities.
Builder supporting interval unions followed by hole subtraction.
One nonempty continuous interval.
Storage and arithmetic precision requested for a linear-algebra operation.
Immutable names and grouping labels for pointwise likelihood contributions.
Adaptive Dormand-Prince 5(4) ODE integration at requested output times.
Integration controls.
First-order ordinary differential equation
y' = f(t,y).Utilities shared by online false-discovery-rate controllers.
A stateful controller for hypotheses arriving in a fixed sequential order.
Immutable record of one online-FDR test.
Function optimization routines.
Immutable numerical-optimization result.
Class to hold optimization results
Accepted L-BFGS path used by Pathfinder approximation selection.
Fits caller-supplied parametric terminal laws directly to European option quotes.
Arbitrage-repaired European option curve and its implied risk-neutral law.
Atom-aware risk-neutral law recovered from a convex piecewise-linear call curve.
Option-price likelihood factors and posterior-predictive distribution adapters.
Immutable European option quote used by the narrow option-implied layer.
Order distribution.
Exact minimum or maximum of independent identically distributed variables.
Bivariate copula adapter exposing conditional CDFs and their inverses.
Replica exchange using random-walk within-temperature transitions.
Cold-chain draws and adjacent-temperature swap diagnostics.
A differentiable map from unconstrained coordinates to constrained values.
Posterior summary and modern multi-chain convergence diagnostics.
Immutable parameter metadata in a compiled Bayesian model.
Pareto-tail smoothing for log importance ratios, with a diagnostic shape estimate.
Multi-path quasi-Newton Gaussian approximation with mixture scoring and PSIS resampling.
Multi-path Gaussian approximation, PSIS diagnostic, and resampled draws.
L-BFGS path plus local Gaussian draw for robust chain initialization.
Immutable controls for multi-path Pathfinder initialization and sampling.
Quasi-Newton Gaussian initialization result.
Exact iid-observation extrema and simulated drawdowns for iid discrete-time increments.
Continuous phase-type law with an optional atom at zero.
Immutable column-pivoted Householder QR factorization.
Model contract required by pointwise predictive assessment.
Pointwise log likelihoods with retained chain boundaries and observation metadata.
Evaluates ordered observation-level log-likelihood contributions.
Sum of independent Bernoulli trials with unequal success probabilities.
Poisson-inverse Gaussian distribution from
actuar.Polya-Aeppli count: Poisson clusters with shifted-geometric cluster sizes.
Mathlib : A C Library of Special Functions
Copyright (C) 1998 Ross Ihaka
Copyright (C) 2000-2007 the R Development Core Team
Copyright (C) 2004 The R Foundation
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
A Java object that represents polynomials as arrays of numerical coefficients.
Checkpoint plus the fingerprints and platform metadata needed to validate a resume.
Restored RJ checkpoint plus the fingerprints and platform recorded with it.
Restored sparse checkpoint plus its model/options fingerprints and platform.
Normal distribution left-truncated at zero.
Positive tempered-stable subordinator increment with Laplace exponent.
Chunked deterministic continuation based on MCSE, never on R-hat alone.
Deterministically extended chain and the reason continuation stopped.
Stopping goal for one posterior coordinate, guarded by minimum draws and chunk count.
Optimizes simplex weights for stacking pointwise out-of-sample predictions.
Reusable FP64 Cholesky factor that can solve multiple right sides in place.
Reusable FP64 CSR handle; capabilities report whether storage is provider-resident.
Reusable FP64 dense matrix handle; providers may retain storage on device.
Reusable FP32 Cholesky factor that can solve multiple right sides in place.
Reusable FP32 CSR handle; capabilities report whether storage is provider-resident.
Reusable FP32 dense matrix handle; providers may retain storage on device.
Symbolically analyzed FP32 sparse Cholesky handle with reusable numeric factors.
A logistic-regression data set prepared for repeated batched evaluation.
Symbolically analyzed FP64 sparse Cholesky handle with reusable numeric factors.
A row-by-feature matrix retained for repeated
X'v score batches.Advisory probes for user-supplied probability kernels.
Immutable interval containing a requested probability under a stated rule.
Model factor instrumented with low-overhead call, time, and non-finite counters.
Lightweight callback invoked after a completed sampler transition.
Forward projection-predictive variable selection for Gaussian linear reference models.
Pareto-smoothed importance-sampling leave-one-out cross-validation.
Optional exact or refitted LOO calculation used when importance sampling is unreliable.
Deprecated.
Matrix utilities
Implementation of CMWC4096 (Complementary-multiply-with-carry) random number generator
by George Marsaglia.
Space and time efficiently computes a sorted Simple Random Sample Without Replacement (SRSWOR), that is, a sorted set of n random numbers from an interval of N numbers;
Example: Computing n=3 random numbers from the interval [1,50] may yield the sorted random set (7,13,47).
Reusable Gaussian random-walk Metropolis transition kernel.
Isotropic Gaussian random-walk Metropolis with warmup scale adaptation.
Implementation of WELL 44497b (Well Equidistributed Long-period Linear) random number generator
by Francois Panneton, et al.
Rayleigh distribution
Taken from VGAM package of R
Reference Black-Scholes/Bachelier transformations and checked inversion.
Proposal distribution and certified majorization constant for rejection
sampling.
Locally informed candidate proposal using a prepared
X'v product.Sampler capable of restoring algorithm-specific adaptive state.
Builds a scalar expression from parameter handles on a reverse-mode tape.
Reusable reverse-mode value-and-gradient evaluator.
Reusable reverse-mode log density suitable for HMC and NUTS.
Allocation-conscious reverse-mode automatic-differentiation tape.
Reverse Weibull distribution.
Deterministic parallel execution with one independently adaptive RJ sampler per chain.
Exact in-memory RJ restart point including ragged state, schedule, adaptation, and RNG.
Checksummed portable persistence for complete reversible-jump restart state.
Model occupancy, movement, inclusion, conditional-parameter, and reliability diagnostics.
Multi-chain diagnostics for ragged reversible-jump output.
Streaming sink for ragged retained RJ draws.
Tidy CSV export for ragged model-specific parameters.
Per-iteration within-model and trans-dimensional transition statistics.
Named parameter schema for one model in a trans-dimensional target.
One dimension-changing or structure-changing reversible proposal.
Posterior summary conditional on a ragged parameter being present.
Progress callback for one trans-dimensional chain.
Transactional RJ proposal including all non-schedule Hastings terms.
Immutable ragged RJMCMC draws, transition statistics, diagnostics inputs, and restart state.
General Java-only RJMCMC acceptance engine with warmup-frozen move and within-model adaptation.
Creates one independently mutable reversible-jump sampler per chain.
Warmup, retention, schedule-adaptation, and streaming options for RJMCMC.
Immutable model identifier and its dimension-specific parameter vector.
Complete normalized joint density and schemas across a family of models.
A fixed-model update scheduled between trans-dimensional proposals.
Outcome of one within-model transition in an RJ schedule.
Rice (Rician) distribution with scale
sigma and distance nu.Whether observations are already losses or are returns (loss is minus return).
Auxiliary-variable proposal used to create a newly active scalar parameter.
Bivariate 90, 180 (survival), or 270 degree rotation of a copula.
Immutable provenance record for reproducing one inference run.
Stateful constant-candidate-threshold SAFFRON online-FDR controller.
Common contract for a reproducible MCMC chain.
Versioned sampler-specific adaptation state for exact resumability.
Cross-chain sampler health summary.
Immutable common MCMC warmup, retention, adaptation, and safety options.
Sampling algorithm currently selected by a numerical distribution.
Source-located modeling-language diagnostic.
Values and first-order parameter sensitivities returned by a numerical solver.
Ranks posterior coefficient draws by practical-significance probability.
Seeded simulation-based calibration rank utility.
Backend-neutral FP32 BLAS, sparse-BLAS, and reusable factorization surface.
Immutable FP64 thin singular-value decomposition
A = U*S*Vt.Four-parameter sinh-arcsinh distribution of Jones and Pewsey.
Difference of two independent Poisson variates.
Skewed T distribution, from skewt package
Location-scale slash distribution,
mu + sigma * Z / U.Coordinate-wise stepping-out and shrinkage slice sampler.
Smooth risk-neutral density plus regularization and differentiation diagnostics.
This class deals with smoothing of cubic B-Splines.
Smooth spline criterion.
NO_CRITERION = No additional minimizing criterion
GCV = Generalized Cross Validation
CV = Cross Validation
DF_MATCH = Degree of freedom matching
NO_CRITERION = No additional minimizing criterion
GCV = Generalized Cross Validation
CV = Cross Validation
DF_MATCH = Degree of freedom matching
Candidate selected by a normalized sparse birth proposal.
Normalized proposal over candidates inactive in the conditioning model.
Immutable FP64 sparse Cholesky factor with reusable solves.
Dimension-matching proposal for a coefficient born into a sparse model.
Fill-reducing ordering used before a sparse symmetric factorization.
Supplies the row score vector used by a locally informed sparse proposal.
Exact sparse RJ restart state, adaptation, counters, RNG, and online summaries.
Checksummed, forced, atomic persistence for complete sparse RJ restart state.
Streaming callback for retained sparse draws.
Crash-safe segment export for ragged sparse draws.
Per-transition statistics for sparse subset RJMCMC.
Complete normalized log joint for an arbitrary sparse candidate universe.
Progress callback for one restartable sparse RJMCMC segment.
One bounded sparse RJ segment plus its exact continuation checkpoint.
Allocation-conscious add/drop/swap RJMCMC for very large sparse candidate universes.
Global warmup target and bounded transition segment for restartable sparse RJMCMC.
Immutable sparse subset, common parameters, and active coefficients.
Online occupancy and conditional-coefficient summary stored in a sparse checkpoint.
Sparse subset target with an arbitrary candidate count and a bounded active set.
Univariate alpha-stable law in Nolan's S1 parameterization.
Java implementation of a forward-declared Stan function.
Adaptive A-stable BDF1 integrator for stiff first-order ODE systems.
Stiff integration controls.
Student-t copula parameterized by correlation and degrees of freedom.
Adds one uniformly selected inactive candidate using a declared birth proposal.
Drops one uniformly selected active candidate with the matching reverse birth density.
Complete normalized log joint for one active-variable subset.
Factory for the standard add/drop/swap subset-selection RJ schedule.
Bit-mask model family for Java-only covariate, locus, or feature selection.
Exchanges one active and inactive candidate while preserving model dimension.
Common-start grouping required to interpret nested R-hat.
Distribution object exposing its smallest enclosing support interval.
Immutable FP64 eigendecomposition of a real symmetric matrix.
Immutable pivoted
P*A*P' = L*D*L' factorization with 1x1/2x2 D blocks.Side of a scalar distribution used by tail and stress calculations.
Log density split into an untempered base (usually the prior) and likelihood.
Distribution exposing stable log characteristic and cumulant transforms.
Open/closed interval on which a cumulant-generating function exists.
Reusable one-step Markov kernel used by chains and meta-samplers.
Triangular distribution with minimum
a, maximum b, and
mode c.Continuous distribution conditioned to lie in a nonempty interval.
Computes the probability and quantile that the maximum of rr studentized
ranges, each based on cc means and with df degrees of freedom
for the standard error, is less than q.
Tukey lambda distribution defined by its symmetric quantile function.
Immutable heterogeneous tuple for Java data adapters and external functions.
Translated from Tweedie package
version 2.2.1, dated 2014-06-06, by Roby Joehanes
Portable element-wise operations supported by accelerator backends.
A uniform proposal for a finite interval with a certified density bound.
Uniform proposal over currently inactive sparse candidates.
Abstraction of a function with one parameter
Utility functions to mimic R
Variance-gamma law X=mu+theta*G+sigma*sqrt(G)*Z, G~Gamma(shape,1).
Common contract for pair-copula vine constructions.
Result of sequential pair-family selection for a simplified vine.
Sequential simplified C-vine and D-vine fitting with pair-family selection.
Monte Carlo lower-orthant probability returned by a vine copula.
Simplified regular-vine structures implemented by JDistlib.
Widely applicable information criterion from pointwise log-likelihood draws.
Fingerprinted metric/step-size warmup reuse, treated as an initial guess by default.
Immutable summary of MCMC adaptation.
Stan-style fast/slow/final warmup schedule with expanding metric windows.
Progress listener retaining lightweight step-size and schedule traces.
Four-parameter Wiener first-passage (drift-diffusion) density used by Stan.
SYNOPSIS
#include <Rmath.h>
double dwilcox(double x, double m, double n, int give_log)
double pwilcox(double x, double m, double n, int lower_tail, int log_p)
double qwilcox(double x, double m, double n, int lower_tail, int log_p);
double rwilcox(double m, double n)
DESCRIPTION
dwilcox The density of the Wilcoxon distribution.
Wishart distribution on symmetric positive-definite matrices.
Mean/size negative binomial with an additional structural-zero probability.
Poisson distribution with an additional structural-zero probability.
Mean/size negative binomial conditional on a positive count.
Poisson distribution conditional on a positive count.
Zipf distribution
Parts taken from VGAM