SimJoint

Simulate Joint Distribution

Simulate multivariate correlated data given nonparametric marginals and their covariance structure characterized by a Pearson or Spearman 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 (1982) approach <doi:10.1080/03610918208812265> and the Ruscio-Kaczetow iteration (2008) <doi:10.1080/00273170802285693>. Package functions are carefully implemented in C++ for squeezing 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 substantial margins. Benchmarks are detailed in function examples. A simple heuristic algorithm is additionally designed to optimize the joint distribution in the post-simulation stage. This heuristic demonstrated not only strong capability of cost reduction, but also good potential of achieving the same level of precision of approximation without the enhanced Iman-Conover-Ruscio-Kaczetow.

Total

0

Last month

0

Last week

0

Average per day

0

Daily downloads

Total downloads

Description file content

Package
SimJoint
Type
Package
Title
Simulate Joint Distribution
Version
0.2.2
Author
Charlie Wusuo Liu
Maintainer
Charlie Wusuo Liu
Description
Simulate multivariate correlated data given nonparametric marginals and their covariance structure characterized by a Pearson or Spearman 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 (1982) approach and the Ruscio-Kaczetow iteration (2008) . Package functions are carefully implemented in C++ for squeezing 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 substantial margins. Benchmarks are detailed in function examples. A simple heuristic algorithm is additionally designed to optimize the joint distribution in the post-simulation stage. This heuristic demonstrated not only strong capability of cost reduction, but also good potential of achieving the same level of precision of approximation without the enhanced Iman-Conover-Ruscio-Kaczetow.
License
GPL-3
Encoding
UTF-8
LazyData
true
Imports
Rcpp (>= 1.0.0), RcppParallel
LinkingTo
Rcpp, RcppParallel, RcppArmadillo
SystemRequirements
GNU make
Suggests
R.rsp
VignetteBuilder
R.rsp
NeedsCompilation
yes
Packaged
2019-08-07 20:25:02 UTC; i56087
Repository
CRAN
Date/Publication
2019-08-07 22:40:20 UTC

install.packages('SimJoint')

0.2.2

4 months ago

Charlie Wusuo Liu

GPL-3

Imports

Rcpp (>= 1.0.0), RcppParallel

Suggests

R.rsp

Discussions