Building models with SAS Enterprise Miner, SAS Factory Miner, SAS Visual Data Mining and Machine Learning or just with programming

Interpreting CCC values in a Cluster Analysis

Reply
Occasional Contributor
Posts: 11

Interpreting CCC values in a Cluster Analysis

Hi! 

It's my first encounter with the CCC. I'm trying to figure out the outflow model. I am a beginner and met this clustering assessment. Can you explain in simple terms how best to interpret this estimate?
I'm not very good at English specialized literature, find SAS TR A-108, but can't understand main point.

image.png

Thank you!

SAS Employee
Posts: 50

Re: Interpreting CCC values in a Cluster Analysis

Posted in reply to DavidBesaev

Hello DavidBesaev -

 

Here is a link to the technical report that you mentioned.

 

A-108 Cubic Clustering Criterion

http://support.sas.com/kb/22/addl/fusion_22540_1_a108_5903.pdf

 

The best place to look for information about how to interpret is in the Conclusion section, printed page 49. Here is a brief summarization:

 

  • Peaks in the plot of the cubic clustering criterion with values greater than 2 or 3 indicate good clusters;
  • Peaks with values between 0 and 2 indicate possible clusters.
  • Large negative values of the CCC can indicate outliers.

 

Pages 40-48 give some examples of interpretations.

 

Another good place to look for interpretation examples is the Getting Started section, and the Examples section, of the chapter The CLUSTER Procedure.

 

        SAS/STAT User's Guide - Procedures

        https://support.sas.com/documentation/onlinedoc/stat/indexproc.html

 

     

Have a great day.

Occasional Contributor
Posts: 11

Re: Interpreting CCC values in a Cluster Analysis

Posted in reply to MikeStockstill

Thank you so much for your help, MikeStockstill !

I will try to get to know these sources more closely.

So, if we look at my plot of CCC, that good performance will be, if there are more than 4 clusters ( more 2000 points)?

 

image.png

Thank you! 

Ask a Question
Discussion stats
  • 2 replies
  • 311 views
  • 0 likes
  • 2 in conversation