Pages: [1]
  Print  
Author Topic: Decide for number of clusters  (Read 243 times)
bp
Newbie
*
Posts: 6


« on: September 25, 2013, 02:51:22 PM »

Hello,

I have extracted SSE, Avg. Sil width and Davies&Bouldin for 20 iterations on my data. The result table is below. I'm confused regarding choosing best k, since each method supports different k. Any idea/hint what should I do more?

kSSEASWDB
20.374920.897440.87625
30.193610.850021.37602
40.139990.760051.48418
50.077120.770311.60937
60.05790.765181.68158
70.034980.485121.84476
80.029390.578711.67001
90.019290.603161.62707
100.0170.603721.61378
110.01750.608471.94819
120.013210.622441.66382
130.011970.631131.81006
140.010560.633781.80031
150.008450.646451.89968
160.009280.653621.69712
170.006180.655961.65225
180.005810.655961.59732
190.006050.651031.71599
200.004330.665391.68256

Kind regards,
Logged
Pages: [1]
  Print  
 
Jump to: