dcor.circular: circular distance correlation function

In CircMLE: Maximum Likelihood Analysis of Circular Data

Description

Perform a distance correlation between circular datasets or between circular and linear datasets.

Usage

dcor.circular(x, y, method = "chord", type = "c-c", ...)

Arguments

x	A vector of class 'circular', or numeric vector of angles measured in radians
y	A vector of class 'circular', numeric vector of angles measured in radians, or numeric vector
method	the distance measure to be used. This must be one of the following functions: ‘"angularseparation"’, ‘"chord"’, '"geodesic"’, or '"circ.range"' (default = "chord"). see ?dist.circular for additional details.
type	if ‘type == "c-c"’ then perform a circular-circular distance corellation, else if ‘type == "c-l"’ then perform a circular-linear distance corellation (default = "c-c").
...	additional parameters passed to the dcor.test function

Value

Same as from the dcor.test function: a list with class ‘htest’containing

method: description of test

statistic: observed value of the test statistic

estimate: dCov(x,y) or dCor(x,y)

estimates: a vector: [dCov(x,y), dCor(x,y), dVar(x), dVar(y)]

replicates: replicates of the test statistic

p.value: approximate p-value of the test

n: sample size

data.name: description of data

See Also

dcor dcov DCOR dcor.test dist.circular

Examples

# Circular-circular distance corellation
x <- circular::rvonmises(n = 50, mu = circular::circular(0), kappa = 3)
y <- x + circular::rvonmises(n = 50, mu = circular::circular(pi), kappa = 10)
dcor.circular(x, y)

# Run permutation test with 9999 iterations
dcor.circular(x, y, R = 9999)

# Circular-linear distance corellation
x <- circular::rvonmises(n = 50, mu = circular::circular(0), kappa = 3)
y <- as.numeric(x) + rnorm(50, mean = 5, sd = 2)
dcor.circular(x, y, type = "c-l", R = 9999)

CircMLE documentation built on Sept. 2, 2020, 1:07 a.m.