evalPoints: Matrix of coordinates

In gremes: Estimation of Tail Dependence in Graphical Models

Matrix of coordinates

Description

Generates a matrix of evaluation points, used by the extremal coefficients estimator.

Usage

evalPoints(obj, ...)

## S3 method for class 'Coordinates'
evalPoints(obj, obj2, x, ...)

## S3 method for class 'RootDepSet'
evalPoints(obj, x, U, ...)

Arguments

obj	Object of class Tuples, Triples, Quadruples, Adjacent which are subclasses of class Coordinates or an object of class RootDepSet.
...	additional arguments
obj2	Object of class Tree
x	A named vector of coordinates of length |U|, where U is the set of nodes with available data.
U	The set of nodes with observable data

Value

An object of the same class as the argument obj containing a matrix of coordinates.

Examples

# create an object of class Adjacent
adjobj<- Adjacent()
# create a graph with named vertices
g<- graph(c("a", "b", "b", "c", "b", "d"), directed = FALSE)
# create a dataset with named columns
mydata<- matrix(rnorm(10*4), ncol=4, nrow=10)
colnames(mydata)<- get.vertex.attribute(g, "name", V(g))
# create object of class Network
mytree<- Tree(g, mydata)
# create the vector of coordinates and name it
x<- c(1:vcount(g))
names(x)<- c("a", "b", "c", "d")
# create the matrix of adjacent coordinates
mycoord<- evalPoints(adjobj, mytree, x)

# create a matrix of pair coordinates
mytup<- Tuples()
mytup<- evalPoints(mytup, mytree, x)

# create matrix of coordinates when there are missing data nodes
mydata<- matrix(rnorm(10*3), ncol=3, nrow=10)
colnames(mydata)<- c("b", "c", "d")
mytree<- Tree(g, mydata)
x<- c(1:vcount(g))
names(x)<- c("a", "b", "c", "d")
mytrip<- Triples()
evalPoints(mytrip, mytree, x)
# create a matrix of coordinates for an arbitrary subsets
rdsobj<- RootDepSet()
rds_values<- list(b=c("c", "d"), c=c("b", "d"), d=c("b", "c"))
rds_roots<- c("c", "d", "b")
rdsobj<- setRootDepSet(rdsobj, rds_values, rds_roots)
x<- c(2,3,4)
names(x)<- c("b", "c", "d")
evalPoints(rdsobj, x, getNodesWithData(mytree))

gremes documentation built on Feb. 16, 2023, 8:06 p.m.