turn on suggestions

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

Showing results for

- JMP User Community
- :
- Discussions
- :
- Discussions
- :
- curve fit for multi variables equation

Topic Options

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

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

Oct 13, 2014 1:19 AM
(1653 views)

I have some results, I want to use curve fit to find the equation which can describe the relation between the variables.I have three(3) variables so the equation should has this format " y=f( x1, x2, x3 ) " . I would be appreciate if you lead me how can I use curve fit to find an equation with three variables?

2 REPLIES

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

Oct 13, 2014 8:47 AM
(1447 views)
| Posted in reply to message from adel_hassanvand 10/13/2014 04:19 AM

Adel, I would start with the "Fit Model" platform and discover the best equation for y=f(X1, X2, X3). Then, it will be a pretty easy exercise to plot your data on a 3-D graph.

Steve

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

Oct 22, 2014 5:38 AM
(1447 views)
| Posted in reply to message from adel_hassanvand 10/13/2014 04:19 AM

Adel,

Have you fit the model and then saved the prediction formula? If so, you can go to your data table and right click on the column header for the prediction formula and then select "Formula" from the list. This will show the formula in the format you suggest above, keeping in mind that Y is implied. If you want to see how predictive your model is go to the Fit YbyX platform and then put the original Y data in Y Response and the saved prediction formula in X Factor and click OK. You can then go to the red hot spot by Bivariate fit and select Fit Line to get fit statistics.