SimJoint: Simulate Joint Distribution

Simulate multivariate correlated data given nonparametric marginal distributions and their covariance structure characterized by a correlation matrix. The simulator engages the problem from a purely computational perspective. It assumes no statistical models such as copulas or parametric distributions, and can approximate the target correlations regardless of theoretical feasibility. The algorithm integrates and advances the Iman-Conover approach (1982) <doi:10.1080/03610918208812265> and the Ruscio-Kaczetow iteration (2008) <doi:10.1080/00273170802285693>. Package functions are carefully implemented in C++ for pushing computing speed, suitable for large input in a manycore environment. Precision of the approximation and computing speed both outperform various CRAN packages to date by a substantial margin. Benchmarks are detailed in function examples. Additionally, a simple heuristic algorithm initially designed to optimize the simulated joint distribution demonstrated not only strong error reduction capability, but also the potential of achieving the same level of precision of approximation without the enhanced Iman-Conover-Ruscio-Kaczetow as a primer, especially when the functional relationships between marginal distributions are highly nonlinear.

Version: 0.2.1
Imports: Rcpp (≥ 1.0.0), RcppParallel
LinkingTo: Rcpp, RcppParallel, RcppArmadillo
Suggests: R.rsp
Published: 2019-06-18
Author: Charlie Wusuo Liu
Maintainer: Charlie Wusuo Liu <liuwusuo at>
License: GPL-3
NeedsCompilation: yes
SystemRequirements: GNU make
CRAN checks: SimJoint results


Reference manual: SimJoint.pdf
Vignettes: SimulatedJointDistribution
Package source: SimJoint_0.2.1.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
OS X binaries: r-release: SimJoint_0.2.1.tgz, r-oldrel: SimJoint_0.2.1.tgz
Old sources: SimJoint archive


Please use the canonical form to link to this page.