Gaussian process regression with an emphasis on kernels. Quantitative and qualitative inputs are accepted. Some pre-defined kernels are available, such as radial or tensor-sum for quantitative inputs, and compound symmetry, low rank, group kernel for qualitative inputs. The user can define new kernels and composite kernels through a formula mechanism. Useful methods include parameter estimation by maximum likelihood, simulation, prediction and leave-one-out validation.
| Version: | 0.5.1 |
| Depends: | Rcpp (≥ 0.10.5), methods, testthat, nloptr, lattice |
| Imports: | MASS, numDeriv, stats4, doParallel, doFuture, utils |
| LinkingTo: | Rcpp |
| Suggests: | DiceKriging, DiceDesign, lhs, inline, foreach, knitr, ggplot2, reshape2, corrplot |
| Published: | 2020-02-05 |
| Author: | Yves Deville, David Ginsbourger, Olivier Roustant. Contributors: Nicolas Durrande. |
| Maintainer: | Olivier Roustant <roustant at insa-toulouse.fr> |
| License: | GPL-3 |
| NeedsCompilation: | yes |
| CRAN checks: | kergp results |
| Reference manual: | kergp.pdf |
| Package source: | kergp_0.5.1.tar.gz |
| Windows binaries: | r-devel: kergp_0.5.1.zip, r-release: kergp_0.5.1.zip, r-oldrel: kergp_0.5.1.zip |
| macOS binaries: | r-release: kergp_0.5.1.tgz, r-oldrel: kergp_0.5.1.tgz |
| Old sources: | kergp archive |
Please use the canonical form https://CRAN.R-project.org/package=kergp to link to this page.