cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
JMP is taking Discovery online, April 16 and 18. Register today and join us for interactive sessions featuring popular presentation topics, networking, and discussions with the experts.
Choose Language Hide Translation Bar

How to fit model?

Hi All, Could you please advice how to fit both linear regression and polynomial (degree=3) model together? Thank you.
1 ACCEPTED SOLUTION

Accepted Solutions
ms
Super User (Alumni) ms
Super User (Alumni)

Re: How to fit model?

I am not sure exactly what you want to do, but it should be quite straightforward.

In the Fit Model platform select Y variable(s), click "Y". Select linear effect and click "Add", select polynomial effect and enter "3" in the "Degree" field and finally select "Polynomial to Degree" in the "Macros" drop-down menu.

View solution in original post

4 REPLIES 4
ms
Super User (Alumni) ms
Super User (Alumni)

Re: How to fit model?

I am not sure exactly what you want to do, but it should be quite straightforward.

In the Fit Model platform select Y variable(s), click "Y". Select linear effect and click "Add", select polynomial effect and enter "3" in the "Degree" field and finally select "Polynomial to Degree" in the "Macros" drop-down menu.

Re: How to fit model?

MS, Thank you for you advice. I would like to explain more what I want to do.
I have 3 input values (x1,x2 and x3) and the output y variable.
As I plot and fit the relations:
(x1,y) = linear regression,
(x2,y) = linear regression,
(x3,y) = polynomial degree=3.
So I would like to get transfer function for prediction the output Y.
I'm not sure which method should I use to get prediction formula by use fit model or neural net. Could you please advice more?
Thank a lot!

Message was edited by: TT
ms
Super User (Alumni) ms
Super User (Alumni)

Re: How to fit model?

I have only little experience with neural nets, however as you seem to have a clear idea about your model and it's essentially linear I suggest Fit Model platform. Neural Net is more useful if the functional relationships are unknown or highly latent, at least that's my impression.

Anyway, after you set up run your model in Fit Model you can get the prediction formula by choosing Save columns/Prediction Formula under the red triangle in the result window.

Re: How to fit model?

Thanks again MS. I will try as your suggestion.