Tuning of the bandwidth parameter in the von Mises-Fisher kernel for (hyper-)spherical data

Share:

Description

Tuning of the bandwidth parameter in the von Mises-Fisher kernel for (hyper-)spherical data whit cross validation.

Usage

1
vmfkde.tune(x, low = 0.1, up = 1)

Arguments

x

A matrix with the data in Euclidean cordinates, i.e. unit vectors.

low

The lower value of the bandwdith to search.

up

The upper value of the bandwdith to search.

Details

Fast tuning of the bandwidth parameter in the von Mises-Fisher kernel for (hyper-)spherical data via cross validation.

Value

A vector including two elements:

Optimal h

The best H found.

cv

The value of the maximised pseudo-likelihood.

Author(s)

Michail Tsagris

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

References

Garcia Portugues E. (2013). Exact risk improvement of bandwidth selectors for kernel density estimation with directional data. Electronic Journal of Statistics, 7, 1655–1685.

Wand M. P., and Jones M. C. (1994). Kernel smoothing. Crc Press.

See Also

vmf.kde,vmf.kerncontour, vm.kde, vmkde.tune

Examples

1
2
x <- rvmf(100, rnorm(3), 15)
vmfkde.tune(x)

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