uskewFA {uskewFactors}

Mixtures of 'Unrestricted' Skew-t Factor Analyzers via the EM algorithm

Description

Fits a mixture of 'unrestricted' skew-t factor analyzers via the EM algorithm for estimation of model parameters

Usage

uskewFA(x, G, q, init=1, max.it=100)

Arguments

x

A numeric matrix.

G

The number of mixture components to fit.

q

The number of latent factors.

init

This number controls the starting values that are used: (1) k-means, or (2) random.

max.it

The maximum number of iterations of the EM algorithm.

Value

map

A vector of the maximum a posteriori group memberships.

bic

The value of the Bayesian Information Criterion.

zhat

The matrix of estimated probabilities of group membership.

likelihood

A vector containing the value of the complete-data log-likelihood computed at each iteration of the EM algorithm.

Note

This package contains measurements on 200 Swiss banknotes: 100 genuine and 100 counterfeit. The variables are length of bill, width of left edge, width of right edge , bottom margin width and top margin width. All measurements are in millimetres. The data source is noted below.

Author(s)

Paula M. Murray, Ryan P. Browne, and Paul D. McNicholas

Maintainer: Paula M. Murray <[e-mail]>

References

Murray, P.M., Browne, R.P., and McNicholas, P.D. (2014), "Mixtures of 'Unrestricted' Skew-t Factor Analyzers". Arxiv preprint arXiv:1310.6224

See Also

Flury, B. and Riedwyl, H. (1988). Multivariate Statistics: A practical approach. London: Chapman and Hall.

Examples

data("banknote")
x=banknote[,c(5,6)]
# We let max.it=3 for a speedy illustration.
# More 	iterations are needed to ensure
# convergence.
results=uskewFA(x,G=2,q=1,max.it=3)
results