Learn R Programming

kpcalg (version 1.0.1)

Kernel PC Algorithm for Causal Structure Detection

Description

Kernel PC (kPC) algorithm for causal structure learning and causal inference using graphical models. kPC is a version of PC algorithm that uses kernel based independence criteria in order to be able to deal with non-linear relationships and non-Gaussian noise.

Copy Link

Version

Install

install.packages('kpcalg')

Monthly Downloads

24

Version

1.0.1

License

GPL (>= 2)

Maintainer

Petras Verbyla

Last Published

January 22nd, 2017

Functions in kpcalg (1.0.1)

dcov.gamma

Test to check the independence between two variables x and y using the Distance Covariance. The dcov.gamma() function, uses Distance Covariance independence criterion with gamma approximation to test for independence between two random variables.
frml.additive.smooth

Formula for GAM without crossterms
hsic.clust

HSIC cluster permutation conditional independence test
regrVonPS

Check if variable can be regressed to independence on its parents
hsic.gamma

Hilber Schmidt Independence Criterion gamma test
frml.full.smooth

Formula for GAM with crossterms
kernelCItest

Kernel Conditional Independence test
hsic.test

Hilber Schmidt Independence Criterion test
kpc

Estimate the WAN-PDAG using the kPC Algorithm
hsic.perm

Hilber Schmidt Independence Criterion permutation test
regrXonS

Regress set of variables on its parents
udag2wanpdag

Last kPC Algorithm Step: Extend Object with Skeleton to Completed PDAG