predict.matrixqda: Classify Matrix Variate Observations by Quadratic...

In MixMatrix: Classification with Matrix Variate Normal and t Distributions

Classify Matrix Variate Observations by Quadratic Discrimination

Description

Classify matrix variate observations in conjunction with matrixqda.

Usage

## S3 method for class 'matrixqda'
predict(object, newdata, prior = object$prior, ...)

Arguments

object	object of class matrixqda
newdata	array or list of new observations to be classified. If newdata is missing, an attempt will be made to retrieve the data used to fit the matrixqda object.
prior	The prior probabilities of the classes, by default the proportions in the training set or what was set in the call to matrixqda.
...	arguments based from or to other methods

Details

This function is a method for the generic function predict() for class "matrixqda". It can be invoked by calling predict(x) for an object x of the appropriate class.

Value

Returns a list containing the following components:

class

The MAP classification (a factor)

posterior

posterior probabilities for the classes

See Also

matrixlda(), matrixqda(), and matrixmixture()

Examples

set.seed(20180221)
# construct two populations of 3x4 random matrices with different means
A <- rmatrixnorm(30, mean = matrix(0, nrow = 3, ncol = 4))
B <- rmatrixnorm(30, mean = matrix(1, nrow = 3, ncol = 4))
C <- array(c(A, B), dim = c(3, 4, 60)) # combine together
groups <- c(rep(1, 30), rep(2, 30)) # define groups
prior <- c(.5, .5) # set prior
D <- matrixqda(C, groups, prior) # fit model
predict(D)$posterior[1:10, ] # predict, show results of first 10
## S3 method for class "matrixqda"

MixMatrix documentation built on Oct. 1, 2024, 1:07 a.m.