Description Usage Arguments Details Value Author(s) References See Also Examples
Conditional independence test using HSIC and permutation with clusters.
1 2 | hsic.clust(x, y, z, sig = 1, p = 100, numCluster = 10, numCol = 50,
eps = 0.1, paral = 1)
|
x |
first variable |
y |
second variable |
z |
set of variables on which we condition |
sig |
the with of the Gaussian kernel |
p |
the number of permutations |
numCluster |
number of clusters for clustering z |
numCol |
maximum number of columns that we use for the incomplete Cholesky decomposition |
eps |
normalization parameter for HSIC cluster test |
paral |
number of cores used |
Let x and y be two samples of length n. Gram matrices K and L are defined as: K_{i,j} =exp((x_i-x_j)^2/sig^2), L_{i,j} =exp((y_i-y_j)^2/sig^2) and M_{i,j} =exp((z_i-z_j)^2/sig^2). H_{i,j} = delta_{i,j} - 1/n. Let A=HKH, B=HLH and C=HMH. HSIC(X,Y|Z) = Tr(AB-2AC(C+ε I)^{-2}CB+AC(C+ε I)^{-2}CBC(C+ε I)^{-2}C)/n^2. Permutation test clusters Z and then permutes Y in the clusters of Z p times to get Y_{(p)} and calculates HSIC(X,Y_{(p)}|Z). (HSIC(X,Y|Z)>HSIC(X,Y_{(p)}|Z))/p.
hsic.clust() returns a list with class htest containing
method |
description of test |
statistic |
observed value of the test statistic |
estimate |
HSIC(x,y) |
estimates |
a vector: [HSIC(x,y), mean of HSIC(x,y), variance of HSIC(x,y)] |
replicates |
replicates of the test statistic |
p.value |
approximate p-value of the test |
data.name |
desciption of data |
Petras Verbyla (petras.verbyla@mrc-bsu.cam.ac.uk) and Nina Ines Bertille Desgranges
Tillman, R. E., Gretton, A. and Spirtes, P. (2009). Nonlinear directed acyclic structure learning with weakly additive noise model. NIPS 22, Vancouver.
K. Fukumizu et al. (2007). Kernel Measures of Conditional Dependence. NIPS 20. https://papers.nips.cc/paper/3340-kernel-measures-of-conditional-dependence.pdf
hsic.gamma, hsic.perm, kernelCItest
1 2 3 4 5 6 7 8 9 10 11 |
HSIC test of independence
data: Gamma approximation
HSIC = 0.0028224, p-value = 0.002088
sample estimates:
HSIC
0.002822439
HSIC test of independence
data: Permutation approximation
HSIC = 0.0028224, p-value = 0.0198
sample estimates:
HSIC
0.002822439
Specify the number of replicates R (R > 0) to perform the test of
independence
data: index 1, replicates 0
nV^2 = 1.2146, p-value = NA
sample estimates:
dCov
0.06362966
HSIC test of conditional independence
data: Cluster permutation approximation
HSIC = 4.2246e-05, p-value = 0.8218
sample estimates:
HSIC
4.224572e-05
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.