summary.AncReg: Summary of AncReg

In AncReg: Ancestor Regression

Summary of AncReg

Description

Summarize the results of AncReg. For models with degree = 0 only the instantaneous graph is returned and for models with degree > 0 the summary graph is returned as well.

Usage

## S3 method for class 'AncReg'
summary(object, alpha = 0.05, verbose = FALSE, corr = TRUE, ...)

Arguments

object	output from AncReg()
alpha	significance level for determin whether a connection is significant
verbose	should information be printed?
corr	should multiplicity correction be applied?
...	Further arguments passed to or from other methods.

Value

A list containing: If degree = 0:

p.val	A numeric matrix of p-values for the instantaneous graph
graph	A boolean matrix indicating whether one variable affects another instantaneously
alpha	The significance level to avoid cycles

If degree > 0:

inst.p.val	A numeric matrix of p-values for the instantaneous graph
inst.graph	A boolean matrix indicating whether one variable affects another instantaneously
inst.alpha	The significance level to avoid cycles
sum.p.val	A numeric matrix of p-values for the summary graph
sum.graph	A boolean matrix indicating whether one variable affects another

See Also

AncReg, instant_graph, summary_graph, instant_p.val, summary_p.val

Examples

# random DAGS for simulation
set.seed(1234)

p <- 5 #number of nodes
DAG <- pcalg::randomDAG(p, prob = 0.5)

B <- matrix(0, p, p) # represent DAG as matrix
for (i in 2:p){
  for(j in 1:(i-1)){
    # store edge weights
    B[i,j] <- max(0, DAG@edgeData@data[[paste(j,"|",i, sep="")]]$weight)
  }
}
colnames(B) <- rownames(B) <- LETTERS[1:p]

# solution in terms of noise
Bprime <- MASS::ginv(diag(p) - B)

n <- 500
N <- matrix(rexp(n * p), ncol = p)
X <- t(Bprime %*% t(N))
colnames(X) <- LETTERS[1:p]

# fit ancestor regression
fit <- AncReg(X)
# collect ancestral p-values and graph
res <- summary(fit, alpha = 1)
res

AncReg documentation built on Aug. 8, 2025, 7:48 p.m.