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: 
Check out the JMP® Marketplace featured Capability Explorer add-in
Choose Language Hide Translation Bar
rajesh_medisett
rajesh_medisett
Level I

How to compare two or more data sets to find out the similarity between two groups?

Dec 9, 2015 01:26 AM (18559 views)

I have 10 sets of data. Each set having 54 values ranging from 1 to 15. My aim is to compare the 10 sets and say that set 1 is similar to set 8 than other sets etc. Can anyone help me how to use JMP software to solve this issue.

0 Kudos
1 ACCEPTED SOLUTION

Accepted Solutions
txnelson
Super User txnelson
Super User
Solution

Re: How to compare two or more data sets to find out the similarity between two groups?

Dec 9, 2015 09:37 AM (22294 views)  |  Posted in reply to message from rajesh_medisett 12-09-2015

The interactive solution is to:

Open each data table and add a new column called "Set".  Rt mouse click on the column header and choose "Column Information".  Change the Modeling Type to "Nominal".  Then, under the Initialize Data selections, choose "Constant".  Inter in a "1" for the first set, a "2" for the second set, etc.

Once all 10 sets have been modified, then go to Tables==>Concatenation.  This platform will allow you to put all of the sets together.

When all of the sets are together, then go to .   Analyze==>Fit Y by X.  Select your measurement variable as the Y Response and the column "Set" as the X Factor.

Using the options under the red triangles in the displayed output, you can select "Means/Anova"  and "Compare Means" to get the analyses you want

Jim

View solution in original post

1 REPLY 1
txnelson
Super User txnelson
Super User
Solution

Re: How to compare two or more data sets to find out the similarity between two groups?

Dec 9, 2015 09:37 AM (22295 views)  |  Posted in reply to message from rajesh_medisett 12-09-2015

The interactive solution is to:

Open each data table and add a new column called "Set".  Rt mouse click on the column header and choose "Column Information".  Change the Modeling Type to "Nominal".  Then, under the Initialize Data selections, choose "Constant".  Inter in a "1" for the first set, a "2" for the second set, etc.

Once all 10 sets have been modified, then go to Tables==>Concatenation.  This platform will allow you to put all of the sets together.

When all of the sets are together, then go to .   Analyze==>Fit Y by X.  Select your measurement variable as the Y Response and the column "Set" as the X Factor.

Using the options under the red triangles in the displayed output, you can select "Means/Anova"  and "Compare Means" to get the analyses you want

Jim