Changing Standard Error in evalclusters() Method 'gap'
4 views (last 30 days)
Show older comments
Hey! Hopefully a very quick one, just couldn't find the answer in the documentation.
When using evalclusters(), the criterion can be set to 'gap' and the optimal number of clusters can be calculated using gap statistics. Usually one of the options when choosing this method is a Tolerance (Mathematica) or SE.factor (R) that allows the user to determine the number of standard errors used in the calculation of Gap(k). The original paper suggested using a 1-SE rule so I believe this is what MATLAB have chosen, however I need a higher level. Does anyone know if this is something that can be changed in MATLAB, and if so how to go about it?
Thanks :)
Relavent Documentation:
https://uk.mathworks.com/help/stats/clustering.evaluation.gapevaluation-class.html
0 Comments
Answers (0)
See Also
Categories
Find more on Startup and Shutdown in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!