Statistics Toolbox™

inconsistent - Inconsistency coefficient

Syntax

Y = inconsistent(Z)
Y = inconsistent(Z,d)

Description

Y = inconsistent(Z) computes the inconsistency coefficient for each link of the hierarchical cluster tree Z, where Z is an (m-1)-by-3 matrix generated by the linkage function. The inconsistency coefficient characterizes each link in a cluster tree by comparing its length with the average length of other links at the same level of the hierarchy. The higher the value of this coefficient, the less similar the objects connected by the link.

Y = inconsistent(Z,d) computes the inconsistency coefficient for each link in the hierarchical cluster tree Z to depth d, where d is an integer denoting the number of levels of the cluster tree that are included in the calculation. By default, d=2.

The output, Y, is an (m-1)-by-4 matrix formatted as follows.

For each link, k, the inconsistency coefficient is calculated as:

For leaf nodes, nodes that have no further nodes under them, the inconsistency coefficient is set to 0.

Example

rand('state',12);
X = rand(10,2);
Y = pdist(X);
Z = linkage(Y,'single');
dendrogram(Z)

W = inconsistent(Z,3)
W =
    0.1313         0    1.0000         0
    0.1386         0    1.0000         0
    0.1463    0.0109    2.0000    0.7071
    0.2391         0    1.0000         0
    0.1951    0.0568    4.0000    0.9425
    0.2308    0.0543    4.0000    0.9320
    0.2395    0.0748    4.0000    0.7636
    0.2654    0.0945    4.0000    0.9203
    0.3769    0.0950    3.0000    1.1040

References

[1] Jain, A., and R. Dubes, Algorithms for Clustering Data, Prentice-Hall, Englewood Cliffs, NJ, 1988.

[2] Zahn, C.T., "Graph-theoretical methods for detecting and describing Gestalt clusters," IEEE Transactions on Computers, C 20, pp. 68-86, 1971.

See Also

cluster, cophenet, clusterdata, dendrogram, linkage, pdist, squareform

icdf

interactionplot