gmdistribution class -

Gaussian mixture models

Description

An object of the gmdistribution class defines a Gaussian mixture distribution, which is a multivariate distribution that consists of a mixture of one or more multivariate Gaussian distribution components. The number of components for a given gmdistribution object is fixed. Each multivariate Gaussian component is defined by its mean and covariance, and the mixture is defined by a vector of mixing proportions.

Construction

To create a Gaussian mixture distribution by specifying the distribution parameters, use the gmdistribution constructor. To fit a Gaussian mixture distribution model to data, use gmdistribution.fit.

fit	Gaussian mixture parameter estimates
gmdistribution	Construct Gaussian mixture distribution

Methods

cdf	Cumulative distribution function for Gaussian mixture distribution
cluster	Construct clusters from Gaussian mixture distribution
disp	Display Gaussian mixture distribution object
display	Display Gaussian mixture distribution object
fit	Gaussian mixture parameter estimates
mahal	Mahalanobis distance to component means
pdf	Probability density function for Gaussian mixture distribution
posterior	Posterior probabilities of components
random	Random numbers from Gaussian mixture distribution
subsasgn	Subscripted reference for Gaussian mixture distribution object
subsref	Subscripted reference for Gaussian mixture distribution object

Properties

All objects of the class have the properties listed in the following table.

CovType	Type of covariance matrices
DistName	Type of distribution
Mu	Input matrix of means `MU`
NComponents	Number k of mixture components
NDimensions	Dimension d of multivariate Gaussian distributions
PComponents	Input vector of mixing proportions
SharedCov	`true` if all covariance matrices are restricted to be the same
Sigma	Input array of covariances

Objects constructed with fit have the additional properties listed in the following table.

AIC	Akaike Information Criterion
BIC	Bayes Information Criterion
Converged	Determine if algorithm converged
Iters	Number of iterations
NlogL	Negative of log-likelihood
RegV	Value of `'Regularize'` parameter

Copy Semantics

Value. To learn how this affects your use of the class, see Comparing Handle and Value Classes in the MATLAB Object-Oriented Programming documentation.

References

McLachlan, G., and D. Peel, Finite Mixture Models, John Wiley & Sons, New York, 2000.