No packages match

adlaplace - Laplace Approximations Using Automatic Differentiation

Computes Laplace-approximate maximum likelihood for hierarchical and latent Gaussian models. A formula interface specifies observation densities (e.g. Gaussian, negative Binomial), fixed effects, and random terms (independent effects, smoothing terms). Customized response distributions and models for random effects can be specified through a low-level interface or by writing interoperable packages. Derivatives are computed using automatic differentiation with 'CppAD', and used in trust region optimization to find modes of random effects. Derivatives of the Laplace approximation of the log-likelihood are computed using third order contractions and is compatible with custom atomics. The approach follows Kristensen, Nielsen, Berg, Skaug, and Bell (2016) <doi:10.18637/jss.v070.i05>.

Last updated

cppopenmp

6.46 score 1 stars 3 dependents

RCppAD - 'CppAD' C++ Header Files for Automatic Differentiation

Provides the 'CppAD' C++ header library for automatic differentiation, for use by R packages via LinkingTo. Headers are vendored with CRAN-safe defaults and R-safe error handling that does not call std::cerr or std::exit. The two final components of the version number are the 'CppAD' release number.

Last updated

5.84 score 1 stars 5 dependents 250 downloads

geostatsp - Geostatistical Modelling with Likelihood and Bayes

Geostatistical modelling facilities using 'SpatRaster' and 'SpatVector' objects are provided. Non-Gaussian models are fit using 'INLA', and Gaussian geostatistical models use Maximum Likelihood Estimation. For details see Brown (2015) <doi:10.18637/jss.v063.i12>. The 'RandomFields' package is available at <https://web.archive.org/web/20250719184025/https://www.wim.uni-mannheim.de/schlather/publications/software> and <https://github.com/cran/RandomFields>.

Last updated

openblas

5.58 score 68 scripts 703 downloads

geostatsp - Geostatistical Modelling with Likelihood and Bayes

Geostatistical modelling facilities using 'SpatRaster' and 'SpatVector' objects are provided. Non-Gaussian models are fit using 'INLA', and Gaussian geostatistical models use Maximum Likelihood Estimation. For details see Brown (2015) <doi:10.18637/jss.v063.i12>. The 'RandomFields' package is available at <https://web.archive.org/web/20250719184025/https://www.wim.uni-mannheim.de/schlather/publications/software> and <https://github.com/cran/RandomFields>.

Last updated

openblas

5.58 score 68 scripts 703 downloads

admvn - Multivariate Normal CDF and SUN Density with CppAD Derivatives

Evaluates the cumulative distribution function of the multivariate normal distribution using specialized bivariate/trivariate algorithms for dimension <= 3 and Genz quasi-Monte Carlo for higher dimensions, with gradient and Hessian with respect to the upper integration limits computed via CppAD automatic differentiation. Also provides the SUN(2,2), SUN(3,3) and SUN(4,4) densities with gradient and Hessian with respect to a block-Cholesky parameter vector, Gauss-Hermite utilities, and KL minimisation of SUN approximations on weighted quadrature.

Last updated

cppopenmp

5.26 score 1 stars

adlaplaceFem - Finite Element Approximations for Adlaplace

Finite-element approximations for hierarchical models with the adlaplace Laplace approximation framework. Provides tensor-product B-spline FEM ingredients for Matern Gaussian random fields (mass, stiffness, and higher-order Grams), including hierarchical locally refined B-spline bases, design and Gram matrix construction on regular grids, optional terra SpatRaster / SpatVector input, and AD tape builders for random_fem_ssq_* / random_fem_det_*.

Last updated

cpp

5.26 score 1 stars

adlaplaceExample - Example Backend for 'adlaplace'

Provides a minimal example backend package for 'adlaplace'. It demonstrates how to implement and expose model-specific AD tape construction while delegating optimization and Laplace approximation workflows to 'adlaplace'.

Last updated

cpp

4.96 score 1 stars

adlaplaceHgp - Hierarchical Gaussian Processes for 'adlaplace'

Hierarchical and random-slope integrated Wiener process model terms for use with the adlaplace Laplace approximation framework. Provides hiwp, rsiwp, rsiid, rsfpoly, and rsrpoly constructors plus conditional simulation utilities for IWP-style smooths.

Last updated

4.66 score 1 stars

mapmisc - Utilities for Producing Maps

Provides a minimal, light-weight set of tools for producing nice looking maps in R, with support for map projections. See Brown (2016) <doi:10.32614/RJ-2016-005>.

Last updated

4.64 score 52 scripts 700 downloads

diseasemapping - Modelling Spatial Variation in Disease Risk for Areal Data

Formatting of population and case data, calculation of Standardized Incidence Ratios, and fitting the BYM model using 'INLA'. For details see Brown (2015) <doi:10.18637/jss.v063.i12>.

Last updated

3.89 score 28 scripts 491 downloads