pgraph: Compute the Projected Graph

In statcodes/pgraph: Build Dependency Graphs using Projection

Description

pgraph calculate the projected graph

Usage

pgraph(z, f = NULL, method = c("ridge", "lasso", "sam"), cond = TRUE,
  trace = FALSE)

Arguments

z	n * p dimensional matrix
f	n * q factor matrix. Default = 'NULL'.
method	projection method. Default = 'linear'.
cond	whether to create a conditional graph or unconditional graph. Default = TRUE. If cond = FALSE, f must be provided.
trace	whether to trace to estimation process.

Value

a list.

test	distance covariance test object
xeps	residual of the projection of x
yeps	residual of the projection of y

Examples

p=30;
n=120;
tmp=runif(p-1,0.5,1)
s=c(0,cumsum(tmp));
s1=matrix(s,p,p)
cov.mat.true=exp(-abs(s1-t(s1)))
prec.mat.true=solve(cov.mat.true);
a=matrix(rnorm(p*n),n,p)
data.sa=a%*%chol(cov.mat.true);
fit = pgraph(data.sa)
fit2 = pgraph(data.sa, cor = 'dcov')

statcodes/pgraph documentation built on May 30, 2019, 9:42 a.m.