Spherical-spherical correlation {Directional}R Documentation

Spherical-spherical correlation

Description

Correlation between two spherical variables.

Usage

spher.cor(x, y)

Arguments

x

A spherical variable. A matrix with thre columns, each row is a unit vector.

y

A spherical variable. A matrix with thre columns, each row is a unit vector.

Details

A very similar to the classical correlation is calcualted. In addition, a hypothesis test for no correlation is performed. Note, that this is a squared correlation actually, so negative values will never be returned.

Value

A vector including:

R-squared

The value of the squared correlation.

p-value

The p-value of the no correlation hypothesis testing.

Author(s)

Michail Tsagris.

R implementation and documentation: Michail Tsagris mtsagris@uoc.gr and Giorgos Athineou <gioathineou@gmail.com>.

References

Kanti V. Mardia and Peter E. Jupp. Directional statistics, pg. 254–255.

See Also

spher.reg, vmf.mle, circ.cor1, circ.cor2

Examples

x <- rvmf(100, rnorm(3), 10)
y <- rvmf(100, rnorm(3), 10)
spher.cor(x, y)

[Package Directional version 6.6 Index]