cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Try the Materials Informatics Toolkit, which is designed to easily handle SMILES data. This and other helpful add-ins are available in the JMP® Marketplace
Choose Language Hide Translation Bar
ask
ask
Level I

What is the best way to use JMP to do clustering analysis if the data is a mixed model

Dec 2, 2023 06:18 AM (887 views)

What is the best way to use JMP to do clustering analysis if the data is a mixed model with continuous and categorical variables? K-Means seems to just work for continuous variables. Right? Thanks in advance.

0 Kudos
1 REPLY 1
Victor_G
Super User Victor_G
Super User

Re: What is the best way to use JMP to do clustering analysis if the data is a mixed model

Created: Dec 4, 2023 05:57 AM  |  Last Modified: Dec 4, 2023 3:04 AM (833 views)  |  Posted in reply to message from ask 12-02-2023

Hi @ask,

 

K-Means and Normal Mixtures are clustering methods requiring numeric columns only. You can have more details and a comparison between clustering methods here : Overview of Platforms for Clustering Observations

 

If you have a dataset with categorical and numeric columns, you can try the Hierarchical Cluster platform.

In this platform, you have access to various methods (Ward, Average, Centroïd, ...) , and since Hierarchical clustering do not require to specify the number of clusters apriori, this approach is interesting as it can provide an exhaustive overview of the possible links between your observations/samples at different levels.

More infos available here : Clustering | JMP

 

I hope this answer will help you, 

Victor GUILLER

"It is not unusual for a well-designed experiment to analyze itself" (Box, Hunter and Hunter)
0 Kudos