Iterative Clustering Control Panel | JMP 13.2

JMP Support 800.450.0135 (US)

Documentation Feedback
Your feedback is important to us. us any comments about our documentation.

Multivariate Methods • Normal Mixtures • Iterative Clustering Control Panel

•

Iterative Clustering Control Panel

The Control Panel for the Cytometry.jmp data table, with the variables CD3 through MCB as Y, Columns, is shown in Control Panel for Normal Mixtures Method. You can fit various numbers of clusters using the Control Panel iteratively or you can specify a range using the Range of Clusters option.

Control Panel for Normal Mixtures Method

The Normal Mixtures Control Panel has these options:

Locates multivariate outliers. Enter the maximum number of neighbors to examine. When you click OK, plots appear giving distances between each point and that point’s nearest neighbor, second nearest neighbor, up to the maximum nearest neighbor specified.

Caution: The total number of nearest neighbors specified is denoted using a small k. This number is not directly connected to the number of clusters, also sometimes denoted with a small k.

The following options appear beneath the nearest neighbor plots:

Tells JMP to treat excluded rows as excluded in future cluster fits within the given report. For example, if you exclude rows based on nearest neighbor plots or the scatterplot matrix, you must select this option to exclude these rows from cluster fits performed within the report using the Control Panel.

Scatterplot Matrix

Creates a scatterplot matrix in a separate window that uses all of the Y variables.

Save NN Distances

Creates new columns in the data table that give the distances from each row to its kth nearest neighbor.

Removes the Declutter report.

The available clustering methods:

KMeans Clustering

Described in the Iterative Clustering Control Panel in K Means Cluster.

Normal Mixtures

Described in this chapter.

Robust Normal Mixtures

Described in this chapter. See Normal Mixtures NCluster=<k> Report.

Self Organizing Map

Described in Self Organizing Map Control Panel in K Means Cluster.

Number of Clusters

Designates the number of clusters to form.

Range of Clusters (Optional)

Provides an upper bound for the number of clusters to form. If a number is entered here, the platform creates separate analyses for every integer between Number of clusters and the value entered as Range of Clusters (Optional).

Fits the clusters.

Diagonal Variance

Constrains the off-diagonal elements of the covariance matrix to zero. The platform fits multivariate normal distributions that have no correlations between the variables.

Note: The Diagonal Variance option is sometimes necessary to avoid obtaining a singular covariance matrix when there are fewer observations than variables. It can also be used to avoid estimating very large covariance matrices for large numbers of variables.

Outlier Cluster

Fits a cluster to catch outliers that do not fall into any of the normal clusters. If this cluster is created, it is designated Cluster 0, and the count of observations appears in the Cluster Summary report. The distribution of observations that fall in the outlier cluster is assumed to be uniform over the hypercube that encompasses the observations.

The number of independent restarts of the estimation process. Each restart has a different starting value. Independent starts help guard against finding local solutions.

Maximum Iterations

The maximum number of iterations of the convergence stage of the EM algorithm.

Converge Criterion

The difference in the likelihood at which the EM iterations terminate.

•

Help created on 9/19/2017