scoreAdj {mnem} | R Documentation |
Computes the fit (score of a network) of the data given a network matrix
scoreAdj( D, adj, method = "llr", logtype = 2, weights = NULL, trans.close = TRUE, subtopo = NULL, prior = NULL, ratio = TRUE, fpfn = c(0.1, 0.1), Rho = NULL, dotopo = FALSE, P = NULL, oldadj = NULL, modified = TRUE )
D |
data matrix; use modified = FALSE |
adj |
adjacency matrix of the network phi |
method |
either llr if D consists of log odds or disc, if D is binary |
logtype |
log base of the log odds |
weights |
a numeric vector of weights for the columns of D |
trans.close |
if TRUE uses the transitive closure of adj |
subtopo |
optional matrix with the subtopology theta as adjacency matrix |
prior |
a prior network matrix for adj |
ratio |
if FALSE uses alternative distance for the model score |
fpfn |
numeric vector of length two with false positive and false negative rates |
Rho |
optional perturbation matrix |
dotopo |
if TRUE computes and returns the subtopology theta (optional) |
P |
previous score matrix (only used internally) |
oldadj |
previous adjacency matrix (only used internally) |
modified |
if TRUE, assumes a prepocessed data matrix |
transitively closed matrix or graphNEL
Martin Pirkl
D <- matrix(rnorm(100*3), 100, 3) colnames(D) <- 1:3 rownames(D) <- 1:100 adj <- diag(3) colnames(adj) <- rownames(adj) <- 1:3 scoreAdj(D, adj)