IMSL C# Numerical Library

ClusterHierarchical Constructor 

Constructor for ClusterHierarchical.

public ClusterHierarchical(
   double[,] dist,
   int method,
   int transform
);

Parameters

dist
A double symmetric matrix containing the distance (or similarity) matrix.
method
An int identifying the clustering method to use.
transform
An int identifying the type of transformation applied to the measures in dist.

Remarks

On input, only the upper triangular part of dist needs to be present. ClusterHierarchical saves the upper triangular part in the lower triangle. On return, the upper triangular part of dist is restored, and the matrix is made symmetric.

method Description
0Single linkage (minimum distance).
1Complete linkage (maximum distance).
2Average distance within (average distance between objects within he merged cluster).
3Average distance between (average distance between objects in the two clusters).
4Ward's method (minimize the within-cluster sums of squares). For Ward's method, the elements of dist are assumed to be Euclidean distances.

transform Description
0No transformation is required. The elements ofdist are distances.
1Convert similarities to distances by multiplying -1.0.
2Convert similarities (usually correlations) to distances by taking the reciprocal of the absolute value.

See Also

ClusterHierarchical Class | Imsl.Stat Namespace