Processes | Pattern Discovery | Clustering Method

Clustering Method
Use the drop-down menu to select the method used for clustering .
Available options are described in the table below:
This method tends to join clusters with small variances and is biased toward producing clusters with the same variance. 1
The TRIM= n option is recommended ( n = the threshold probability, below which points are omitted).
1
A new dissimilarity measure, d* , is computed based on density estimates and adjacencies.
You must specify one of the following options:
K= n (where n = the number of neighbors for k -nearest neighbor density estimation),
R= n (where n = the radius of sphere of support for uniform-kernel density estimation), or
HYBRID to specify the Wong hybrid clustering method.
Choose this option to use the flexible- beta method developed by Lance and Williams (1967) 3 .
The BETA= n option is recommended ( n = the beta parameter, usually between 0 and -1, -0.25 is specified by default).
Choose this option to use the median method developed by Gower (1967) 5 .
You must specify one of the following options:
K= n (where n = the number of neighbors for k -nearest neighbor density estimation),
R= n (where n = the radius of sphere of support for uniform-kernel density estimation, or
HYBRID to specify the Wong hybrid clustering method.
Choose this method to set the distance between clusters to the ANOVA sum of squares between the two clusters summed over all the variables . At each generation, two clusters from the previous generation are merged to reduce the within-cluster sum of squares over all partitions. The sums of squares are easier to interpret when they are divided by the total sum of squares to give the proportions of variance (squared semipartial correlations).
The TRIM= n option is recommended ( n = the threshold probability, below which points are omitted).

1
Sokal, R.R., and C.D. Michener. (1958) A statistical method for evaluating systematic relationships. University of Kansas Science Bulletin 38: 1409-1438.

2
Milligan, G.W. (1980) An examination of the effect of six types of error perturbation on fifteen clustering algorithms. Psychometrika 45: 325-342.

3
Lance, G. N. and Williams, W. T. (1967) A general theory of classificatory sorting strategies. I. hierarchical systems. Computer Journal 9: 373–380.

4
McQuitty, L. L. (1966) Similarity analysis by reciprocal pairs for discrete and continuous data. Educational and Psychological Measurement 26: 825–831

5
Gower, J. C. (1967) “A Comparison of Some Methods of Cluster Analysis,” Biometrics, 23, 623–637.

To Specify a Clustering Method:
*
*
For Additional Information
Refer to the SAS PROC CLUSTER documentation for more information.