Compute various network statistics from a list sparse precision
matrices. The sparse precision matrix is taken to represent the conditional
independence graph of a Gaussian graphical model. This function is a simple
wrapper for GGMnetworkStats.
GGMnetworkStats.fused(Plist)A list of sparse precision/partial correlation matrix.
A data.frame of the various network statistics for each
class. The names of Plist is prefixed to column-names.
For details on the columns see GGMnetworkStats.
## Create some "high-dimensional" data
set.seed(1)
p <- 10
ns <- c(5, 6)
Slist <- createS(ns, p)
## Obtain sparsified partial correlation matrix
Plist <- ridgeP.fused(Slist, ns, lambda = c(5.2, 1.3), verbose = FALSE)
PCsparse <- sparsify.fused(Plist , threshold = "absValue", absValueCut = 0.2)
#> - Retained elements: 3
#> - Corresponding to 6.67 % of possible edges
#>
#> - Retained elements: 4
#> - Corresponding to 8.89 % of possible edges
#>
SPlist <- lapply(PCsparse, "[[", "sparsePrecision") # Get sparse precisions
## Calculate GGM network statistics in each class
if (FALSE) GGMnetworkStats.fused(SPlist)