# vmf.da: Cross validation for estimating the classification rate of a... In Directional: Directional Statistics

## Description

Cross validation for estimating the classification rate of a discrminant analysis for directional data assuming a von Mises-Fisher distribution.

## Usage

 `1` ```vmf.da(x, ina, fraction = 0.2, R = 200, seed = FALSE) ```

## Arguments

 `x` A matrix with the data in Eulcidean coordinates, i.e. unit vectors. `ina` A variable indicating the groupings. `fraction` The fraction of data to be used as test set. `R` The number of repetitions. `seed` If seed is TRUE, the results will always be the same.

## Details

A repeated cross validation procedure is performed to estimate the rate of correct classification.

## Value

A list including:

 `percent` The estimated percent of correct classification and two estimated standard deviations. The one is the standard devation of the rates and the other is assuming a binomial distribution. `ci` Three types of confidence intervals, the standard one, another one based on the binomial distribution and the third one is the empirical one, which calcualtes the upper and lower 2.5% of the rates.

## Author(s)

Michail Tsagris

R implementation and documentation: Michail Tsagris <[email protected]> and Giorgos Athineou <[email protected]>

## References

Morris, J. E., & Laycock, P. J. (1974). Discriminant analysis of directional data. Biometrika, 61(2): 335-341.

```vmfda.pred, mix.vmf, vmf, dirknn ```
 ```1 2 3``` ```x <- rvmf(100, rnorm(4), 15) ina <- rep(1:2, each = 50) vmf.da(x, ina, fraction = 0.2, R = 200, seed = FALSE) ```