bic {mclust1998}R Documentation

BIC for parameterized MVN mixture models

Description

Bayesian Information Criterion for MVN mixture models with possibly one Poisson noise term.

Usage

bic(data, modelid, ...)

Arguments

data matrix of observations.
modelid An integer specifying a parameterization of the MVN covariance matrix defined by volume, shape and orientation charactertistics of the underlying clusters. The allowed values for modelid and their interpretation are as follows: "EI" : uniform spherical, "VI" : spherical, "EEE" : uniform variance, "VVV" : unconstrained variance, "EEV" : uniform shape and volume, "VEV" : uniform shape.
... other arguments, including a quantity eps for determining singularity in the covariance. The precise definition of eps varies the parameterization, each of which has a default.
Furthermore z, a matrix of conditional probabilities. z should have a row for each observation in data, and a column for each component of the mixture. If z is missing, a single cluster is assumed (all noise if noise = TRUE).
Next argument: equal, a logical variable indicating whether or not the mixing proportions are equal in the model. The default is to assume they are unequal.
The noise logical variable indicates whether or not to include a Poisson noise term in the model. Default : FALSE.
Finally, Vinv gives an estimate of the inverse hypervolume of the data region (needed only if noise = TRUE). Default : determined by the function hypvol.

Value

An object of class "bic" which is the Bayesian Information Criterion for the given mixture model and given conditional probabilites. The model parameters and reciprocal condition estimate are returned as attributes.

NOTE

The reciprocal condition estimate returned as an attribute ranges in value between 0 and 1. The closer this estimate is to zero, the more likely it is that the corresponding EM result (and BIC) are contaminated by roundoff error.

References

C. Fraley and A. E. Raftery, How many clusters? Which clustering method? Answers via model-based cluster analysis. Technical Report No. 329, Dept. of Statistics, U. of Washington (February 1998).

R. Kass and A. E. Raftery, Bayes Factors. Journal of the American Statistical Association90:773-795 (1995).

See Also

me, mstep

Examples

data(iris)
cl <- mhclass(mhtree(iris[,1:4], modelid = "VVV"), 3)
z <- me( iris[,1:4], ctoz(cl), modelid = "VVV")
bic(iris[,1:4], modelid = "VVV", z = z)


[Package Contents]