Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

- JMP User Community
- :
- Discussions
- :
- find possible correlation among variables

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

Highlighted

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

A week ago
(117 views)

Hello everyone,

I'm wondering if someone can help me with the analysis I have to do, since I'm new to this software.

In few words, I have a box let's say and the inputs to this box are A, B and C. The outputs are D, E, F, G, H. Each letter corresponds to a coloumn with many results. For example:

Inputs: A:100 200 300 400

B: 123 456 789 123

Outputs: D:125 147 159 165

E: 14 89 55 63

and so on.

I would like to find if there's a correlation among inputs and outputs and which is the probability that a variable from the outputs comes from a variable of the inputs.

I would be really grateful if someone could answer.

1 REPLY

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

A week ago
(97 views)

A good place to start is with the Multivariate Platform (Analyze/Multivariate Methods/Multivariate ). Just put all your variables into the Y role, and click OK.

One other thing that might be important for you. I suppose you are starting out with data in some other table, not in JMP. In the source program, select the range of data, with the column names on the first row, and copy this to the clipboard. Then in JMP do: File/New/Data Table, Then without doing anything else, don't click on anything in the table, do this: Edit/Paste with Column names. Now you should have a complete dataframe ready to roll with.