Automated Linkage Group Clustering Method

Use the drop-down menu to specify the method to use for joining clusters to form linkage groups via hierarchical clustering. Different algorithms might work better than others depending on your data.

Note: This parameter is available only when Automated Hierarchical Clustering has been selected from the Choose a linkage grouping method options.

Clustering methods are described in the following table:

Clustering Method	Description
Average	Choose this method to define clusters based on the average distance (recombination rate) between pairs of markers from different clusters. This method is specified by default.
Single	Choose this method to define the distance between clusters based on the minimum recombination rate between a marker in one cluster and a marker in a different cluster. This method is often the method used in other linkage grouping software. However, because it can suffer from chaining together spuriously linked markers, this method is biased toward forming imbalanced groups .
Complete	Choose this method to define the distance between clusters based on the maximum recombination rate between a marker in one cluster and a marker in a different cluster. This method is biased toward producing clusters of equivalent diameters and can be distorted by even moderate outliers.

To Specify a Clustering Method:

Specify Automatic Hierarchical Clustering in Choose a linkage grouping method.

Make a selection using the drop-down menu.

Please refer to the SAS PROC CLUSTER documentation for more information.