qpBoundary {qpgraph} | R Documentation |
Calculates and plots the size of the largest vertex boundary as function of the non-rejection rate.
qpBoundary(nrrMatrix, n=NA, threshold.lim=c(0,1), breaks=5, vertexSubset=NULL, plot=TRUE, qpBoundaryOutput=NULL, density.digits=0, logscale.bdsize=FALSE, titlebd="Maximum boundary size as function of threshold", verbose=FALSE)
nrrMatrix |
matrix of non-rejection rates. |
n |
number of observations from where the non-rejection rates were estimated. |
threshold.lim |
range of threshold values on the non-rejection rate. |
breaks |
either a number of threshold bins or a vector of threshold breakpoints. |
vertexSubset |
subset of vertices for which their maximum boundary size is calculated with respect to all other vertices. |
plot |
logical; if TRUE makes a plot of the result; if FALSE it does not. |
qpBoundaryOutput |
output from a previous call to |
density.digits |
number of digits in the reported graph densities. |
logscale.bdsize |
logical; if TRUE then the scale for the maximum boundary size is logarithmic which is useful when working with more than 1000 variables; FALSE otherwise (default). |
titlebd |
main title to be shown in the plot. |
verbose |
show progress on calculations. |
The maximum boundary is calculated as the largest degree among all vertices of a given qp-graph.
A list with the maximum boundary size and graph density as function of threshold, the threshold on the non-rejection rate that provides a maximum boundary size strictly smaller than the sample size n and the resulting maximum boundary size.
R. Castelo and A. Roverato
Castelo, R. and Roverato, A. A robust procedure for Gaussian graphical model search from microarray data with p larger than n. J. Mach. Learn. Res., 7:2621-2650, 2006.
require(mvtnorm) nVar <- 50 ## number of variables maxCon <- 5 ## maximum connectivity per variable nObs <- 30 ## number of observations to simulate set.seed(123) A <- qpRndGraph(p=nVar, d=maxCon) Sigma <- qpG2Sigma(A, rho=0.5) X <- rmvnorm(nObs, sigma=as.matrix(Sigma)) ## the higher the q the less complex the qp-graph nrr.estimates <- qpNrr(X, q=1, verbose=FALSE) qpBoundary(nrr.estimates, plot=FALSE) nrr.estimates <- qpNrr(X, q=5, verbose=FALSE) qpBoundary(nrr.estimates, plot=FALSE)