Hypothesis test for von Mises-Fisher distribution over Kent distribution

Share:

Description

The null hypothesis is whether a von Mises-Fisher distribution fits the data well, where the altenrative is that Kent distribution is more suitable.

Usage

1
fishkent(x, B = 999)

Arguments

x

A numeric matrix containing the data as unit vectors, i.e. in Euclidean coordinates.

B

The number of bootstrap re-samples. By default is set to 999. If it is equal to 1, no bootstrap is performed and the p-value is obtained throught the asymptotic distribution.

Details

Essentially it is a test of rotational symmetry, whether Kent's ovalness parameter (beta) is equal to zero. This works for spherical data only.

Value

A vector including:

test

The value of the test statistic

p-value or Bootstrap p-value

The p-value of the test.

Author(s)

Michail Tsagris

R implementation and documentation: Michail Tsagris <mtsagris@yahoo.gr> and Giorgos Athineou <athineou@csd.uoc.gr>

References

Rivest, L. P. (1986). Modified Kent's statistics for testing goodness of fit for the Fisher distribution in small concentrated samples. Statistics & probability letters, 4(1): 1-4.

See Also

vmf, kent.mle, rkent

Examples

1
2
3
x <- rvmf(100, rnorm(3), 15)
fishkent(x)
fishkent(x, B = 1)

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.