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
- :
- Automate saving of prediction formula using JMP sc...

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
- Permalink
- Email to a Friend
- Report Inappropriate Content

Jul 8, 2011 8:04 AM
(5688 views)

Greetings all,

Hoping that someone with more JMP script-writing experience can offer some suggestions here. What I'd like to do is fit a simple linear regression using the "Fit Model" option, then save the prediction formula for the subsequent model to my current data table automatically through the script. I've been able to do the first part (fit the model), but the second part is proving difficult to figure out.

Any advice would be much appreciated. I'm more familiar with programming in R or STATA, so it's been a process getting used to JSL. Actually, if there are any recommendations for good JSL references (other than the JMP scripting guide, which I find incredibly lacking), that would also be fantastic.

Dan

Solved! Go to Solution.

1 ACCEPTED SOLUTION

Accepted Solutions

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Jul 8, 2011 8:27 AM
(9820 views)

Solution

Hi Dan

Does this solve your problem? It saves the predicted values in a column with a formula attached.

linfit=Fit Model**(**

Y**(** :Yvar **)**,

Effects**(** :Xvar **)**,

Personality**(** Standard Least Squares **)**,

Run model

**)**;

linfit<<prediction formula;

BR, Marianne

10 REPLIES

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Jul 8, 2011 8:27 AM
(9821 views)

Hi Dan

Does this solve your problem? It saves the predicted values in a column with a formula attached.

linfit=Fit Model**(**

Y**(** :Yvar **)**,

Effects**(** :Xvar **)**,

Personality**(** Standard Least Squares **)**,

Run model

**)**;

linfit<<prediction formula;

BR, Marianne

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Jul 8, 2011 8:33 AM
(4910 views)

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Jun 10, 2013 4:53 AM
(4910 views)

*Any advice would be much appreciated. I'm more familiar with programming in R or STATA, so it's been a process getting used to JSL. Actually, if there are any recommendations for good JSL references (other than the JMP scripting guide, which I find incredibly lacking), that would also be fantastic.*

This forum is a great place to learn about JSL. It's not an easy language but it's pretty addicting once you get the hang of it.

The JMPer Cable newsletters have some good JSL examples. JMP | JMP Newsletters

The scripting index in JMP 10 has been beefed up considerably with a ton of example code (Help > Scripting Index).

Also I would recommend going to the JMP conference held in September - great value for the money.

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Mar 3, 2017 6:07 AM
(4814 views)

How would this be modified if a flexible spline fit was to be used

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Mar 3, 2017 7:21 AM
(4811 views)

It is the same method as the previous response

```
Names Default To Here( 1 );
dt = Open( "$SAMPLE_DATA\semiconductor capability.jmp" );
FM=Fit Model(
Y( :NPN1 ),
Effects( :PNP1 & Knotted( 5 ) ),
Personality( "Standard Least Squares" ),
Emphasis( "Minimal Report" ),
Run(
:NPN1 << {Summary of Fit( 1 ), Analysis of Variance( 1 ),
Parameter Estimates( 1 ), Lack of Fit( 0 ), Plot Actual by Predicted( 0 ),
Plot Residual by Predicted( 0 ), Plot Effect Leverage( 0 )}
),
SendToReport(
Dispatch( {"Response NPN1"}, "Effect Details", OutlineBox, {Close( 0 )} )
)
);
fm << prediction formula;
```

Jim

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Jun 10, 2013 5:06 AM
(4910 views)

Hi everybody,

I am looking for to save predicted values of a fit model(Stepwise). Do you can help myself ?

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Mar 3, 2017 7:28 AM
(4809 views)

Here is a sample script for automation of a Stepwise regression

```
Names Default To Here( 1 );
dt = Open( "$SAMPLE_DATA\semiconductor capability.jmp" );
fm = Fit Model(
Y( :NPN1 ),
Effects(
:PNP1,
:PNP2,
:NPN2,
:PNP3,
:IVP1,
:PNP4,
:NPN3,
:IVP2,
:NPN4,
:SIT1,
:INM1,
:INM2,
:VPM1,
:VPM2,
:VPM3,
:PMS1,
:SNM1,
:SPM1,
:NPN5,
:EP2,
:ZD6,
:PBA,
:PLG,
:CAP
),
Personality( "Stepwise" ),
Run
);
fm << Finish;
nfm = fm << run model;
nfm << prediction formula;
```

Jim

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Sep 20, 2017 12:15 PM
(3544 views)

Hi all,

Can I do the same with Fit Curve instead of Fit Model? Below code gives me nothing:

```
nl = Fit Curve(
Y( :Response ),
X( :Dose ),
Fit Logistic 4P Hill( ),
);
nl << prediction formula;
```

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Sep 21, 2017 2:09 AM
(3514 views)

Because (like some other platforms), 'Fit Curve' allows multiple fits in the same report window, you have to tell JMP which curve you want (even if there is only one):

```
NamesDefaultToHere(1);
// Sample data
dt = Open("$SAMPLE_DATA/Nonlinear Examples/Chemical Kinetics.jmp");
// Fit a curve with Nonliear
fc = Fit Curve( Y( :Name( "Velocity (y)" ) ), X( :Concentration ), Fit Logistic 4P Hill );
Wait(2);
// The fitted curve is 'Fit[1]': Save the prediction formula
fc << fit[1](savePredictionFormula);
```