As the first step in the decommissioning of sasCommunity.org the site has been converted to read-only mode.


Here are some tips for How to share your SAS knowledge with your professional network.


Tips:CCC in Proc Cluster

From sasCommunity
Jump to: navigation, search

CCC, otherwise known as Cubic Clustering Criterion (Sarle 1983), is one of the key features that can be derived from the use of PROC CLUSTER.

It can be created by declaring the option CCC at the PROC CLUSTER statement.

PROC CLUSTER DATA = <data to be analyzed> CCC;
    <many lines that needs to be filled in>
    <many lines>
RUN;

Below is the original usage note by SAS. Due to the complexity involved in the analysis, SAS has posted suggestions on the ways of interpreting the results. One of the common approach is to seek the highest peak between 2-3 as the number of clusters in the data. A side benefit of using CCC is the ability to identify outliers in the data when the CCC value is more than -30.

....see also



For more in depth discussion and theoretical knowledge about CCC, you can refer to the original technical document in the read more link below.

....see also


Submitted by Murphy Choy. Contact me at my Discussion Page.