SCCI: Stochastic Complexity-based Conditional Independence...

In SCCI: Stochastic Complexity-Based Conditional Independence Test for Discrete Data

Description

Calculates whether two random variables X and Y are independent given a set of variables Z using SCCI. A score of 0 denotes that independence holds and values greater than 0 mean that X is not independent of Y given Z. For details on SCCI, we refer to Marx and Vreeken (AISTATS, 2019). If you use SCCI in your work, please cite Marx and Vreeken (AISTATS, 19).

The output of SCCI(..) is the difference in number of bits between condtioning X only on Z and conditioning on Z and Y. For the variant of SCCI that gives outputs that can be intpreted as p-values, please refer to pSCCI.

Usage

SCCI(x, y, Z, score="fNML", sym=FALSE)	

Arguments

x	A discrete vector.
y	A discrete vector.
Z	A data frame consisting of zero or more columns of discrete vectors.
score	Default: fNML, optionally qNML can be passed.
sym	sym can be true or false

References

Alexander Marx and Jilles Vreeken; Testing Conditional Independence on Discrete Data using Stochastic Complexity, Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR, 2019

Examples

set.seed(1)
x = round((runif(1000, min=0, max=5)))
y = round((runif(1000, min=0, max=5)))
Z = data.frame(round((runif(1000, min=0, max=5))), round((runif(1000, min=0, max=5))))
SCCI(x=x,y=y,Z=Z,score="fNML",sym=FALSE)	## 0

SCCI documentation built on June 4, 2019, 5:03 p.m.