st: Calinski & Duda stop rule values

[Frank Gallo <fjgallo@mac.com>]

Hi All,

I read the help file for "cluster stop," which reads "The cluster stop  
and clustermat stop commands currently provide two stopping rules, the  
Calinski and Harabasz (1974) pseudo-F index and the Duda and Hart  
(1973) Je(2)/Je(1) index. For both rules, larger values indicate more  
distinct clustering. Presented with the Duda-Hart Je(2)/Je(1) values  
are pseudo-T-squared values. Smaller pseudo-T-squared values indicate  
more distinct clustering."

So, when does one stop with Calinski? The numbers keep getting larger.

-------------------------+
|             |  Calinski/  |
|  Number of  |  Harabasz   |
|  clusters   |  pseudo-F   |
|-------------+-------------|
|      2      |    1093.62  |
|      3      |    1916.22  |
|      4      |    1287.48  |
|      5      |    8708.58  |
|      6      |   69082.54  |
|      7      |   95192.28  |
|      8      |  250063.56  |
|      9      |  432808.79  |
|     10      |  409236.97  |
|     12      |   1.75e+06  |
|     13      |   1.88e+06  |
|     14      |   3.27e+06  |
|     15      |   4.24e+06


So, what's large and what's small with Duda?


+-----------------------------------------+
|             |         Duda/Hart         |
|  Number of  |             |  pseudo     |
|  clusters   | Je(2)/Je(1) |  T-squared  |
|-------------+-------------+-------------|
|      1      |   0.3582    |   5883.18   |
|      2      |   0.0335    |  61958.36   |
|      3      |   0.2286    |   3831.06   |
|      4      |   0.0635    |  12749.90   |
|      5      |   0.0000    |  8.20e+27   |
|      6      |   0.0000    |  3.15e+26   |
|      7      |   0.3275    |    788.36   |
|      8      |   0.0637    |   3863.40   |
|      9      |   0.3981    |    722.72   |
|     10      |   0.2625    |   1280.92   |
+-----------------------------------------+

I have the Calinski, and Milligan references from the help file on  
order. Meanwhile, I would greatly appreciate any guidance. Thank you.

Best,
Frank




*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/