Gaussian Mixture Models

Cluster based on Gaussian mixture models using the Expectation-Maximization algorithm

Gaussian mixture models (GMMs) assign each observation to a cluster by maximizing the posterior probability that a data point belongs to its assigned cluster. Create a GMM object gmdistribution by fitting a model to data (fitgmdist) or by specifying parameter values (gmdistribution). Then, use object functions to perform cluster analysis (cluster, posterior, mahal), evaluate the model (cdf, pdf), and generate random variates (random).

Functions

expand all

Create `gmdistribution` Object

`fitgmdist`	Fit Gaussian mixture model to data
`gmdistribution`	Create Gaussian mixture model

Work with `gmdistribution` Object

`cdf`	Cumulative distribution function for Gaussian mixture distribution
`cluster`	Construct clusters from Gaussian mixture distribution
`mahal`	Mahalanobis distance to Gaussian mixture component
`pdf`	Probability density function for Gaussian mixture distribution
`posterior`	Posterior probability of Gaussian mixture component
`random`	Random variate from Gaussian mixture distribution

Topics

Cluster Using Gaussian Mixture Model
Partition data into clusters with different sizes and correlation structures.
Cluster Gaussian Mixture Data Using Hard Clustering
Implement hard clustering on simulated data from a mixture of Gaussian distributions.
Cluster Gaussian Mixture Data Using Soft Clustering
Implement soft clustering on simulated data from a mixture of Gaussian distributions.
Tune Gaussian Mixture Models
Determine the best Gaussian mixture model (GMM) fit by adjusting the number of components and the component covariance matrix structure.

Gaussian Mixture Models

Functions

Create gmdistribution Object

Work with gmdistribution Object

Topics

Create `gmdistribution` Object

Work with `gmdistribution` Object