topic Re: SVEM Prediction formula in Discussions

SVEM Prediction formula

frankderuyck — Tue, 02 Dec 2025 15:00:16 GMT

I made a SVEM analysis and would like to use the formula to comupute process control ranges using the Design Space Profiler. I saved the prediction formula and can't save a prediction formula with process parameters, only a Mean formula here below?

Is it possible to get an expression as a function of the process parameters that can be used in the design space profiler? Or can I use the Maximum Likelihood expression reported together with SVEM in the GENREG report?

Re: SVEM Prediction formula

Victor_G — Tue, 02 Dec 2025 15:57:36 GMT

Hi @frankderuyck,

When launching the Profiler, click on Expand Intermediate Formulas. This will indicate to JMP that instead of displaying your prediction formula depending on the other sample prediction formula, it has to develop the equation of each sample prediction formula to get to the initial factors.

Hope this answer will solve your problem,

Re: SVEM Prediction formula

MathStatChem — Tue, 02 Dec 2025 17:17:09 GMT

If you create the formula as a sum divided by the number of prediction formulas, you can use that as @Victor_G says, with the expanded formulas option, and then from the profiler you can save the expanded formula as a new column. You can also further simplify that formula (open the formula editor and select "Simplify" from the red triangle). That creates a a prediction formula with each model effect have a single coefficient.

Re: SVEM Prediction formula

MathStatChem — Tue, 02 Dec 2025 17:18:04 GMT

Note you have to use a sum using "+"'s , not the Sum( ) or Mean( ) function for this to work.

Re: SVEM Prediction formula

frankderuyck — Tue, 02 Dec 2025 20:15:52 GMT

I don't find the Expand Intermediate Formulas in the Profiler menu?

Re: SVEM Prediction formula

MathStatChem — Tue, 02 Dec 2025 23:47:56 GMT

It is an option on the launch dialog.

Re: SVEM Prediction formula

frankderuyck — Wed, 03 Dec 2025 07:22:52 GMT

Hi, thanks for your inputs!

I checked both (1) Expand Intermediate fromulas" but this gave the same result as above? Strange that when I click on relaunch the Expand option is not marked, so guess this did not work properly?

I also tried the the Simplify option by going to the Prediction Formula SVEM column, opening the formula editor and clicking on Simplify and the formula remains unchanged as shown above; going back to formula editor I see that Simplify is not marked so I guess this is not active?

I would like to use the SVEM model formula for process control range specification for it is a validated, more reliable & noise-robust model. I will now - with only one response Y - do this directly from the prediction profiler. With more responses Y I will need the profiler.

Re: SVEM Prediction formula

MathStatChem — Wed, 03 Dec 2025 12:56:26 GMT

Are you using Generalized Regression to develop the SVEM model? That platform allows you to save the simplified formula, in version 18 and 19, when you choose "Save Prediction Formula". What you are using are the resampled prediction formulas, I think.

Re: SVEM Prediction formula

frankderuyck — Sat, 06 Dec 2025 11:28:34 GMT

When I click on red triangle and select save colums in menu I only see "Save Resample Formulas"? No simplified prediction formula

Re: SVEM Prediction formula

Victor_G — Sat, 06 Dec 2025 16:12:53 GMT

Hi @frankderuyck

The option "Save Prediction Formula" is only available when the specified distribution is Normal: https://www.jmp.com/support/help/en/19.0/#page/jmp/model-fit-options-for-selfvalidated-ensemble-models.shtml#

Did you try to save the resample formula, and launch the Profiler with the formula and the option "Expand intermediate formula" ? You may have to relaunch the platform, check the option, and then run it: https://www.jmp.com/support/help/en/19.0/#page/jmp/profiler-launch-windows.shtml#ww347639

Re: SVEM Prediction formula

frankderuyck — Mon, 08 Dec 2025 07:09:52 GMT

HI Victor, I tried several times cfr. below

unfortunately this does't work

Strange that, when clicking on relaunch, the expand box is emty?

Re: SVEM Prediction formula

Victor_G — Mon, 08 Dec 2025 08:59:12 GMT

Hi @frankderuyck,

Can you share your datatable or an anonymized version ? Which JMP version are you using ?

I don't understand what is not working. I reproduce the same steps on JMP dataset Powder Metallurgy with a Weibull SVEM Forward regression. I have only the option "Save Resample Formulas" like you have, and it gives me a Pred Formula similar to what you showed :

Do you have also the column property "Expand Intermediates" with the value set at 1 ?

When I launch the Profiler from the Graph menu with the "Expand Intermediate Formulas" :

I obtain a Profiler with the response linked only to the predictors :

You can check you have the same settings as I show here (on JMP version 18.1.2 for me), and if it's not helpful, can you share a dataset so that I can try to see what's not working ?

Best,

Re: SVEM Prediction formula

frankderuyck — Mon, 08 Dec 2025 10:00:05 GMT

Find aatached DOE with SVEM analysis

Re: SVEM Prediction formula

Victor_G — Mon, 08 Dec 2025 12:11:26 GMT

Ok, I understand better.
Some of the "Purity sample prediction formula" in the Profiler corresponds to constant values. These 24 sample predictions values are constant, so they don't have influence when you change factor settings.

Example with Purity Sample 11 Prediction Formula :

What I would suggest is to replace these constant values predictions formula by their values in the Pred Formula Purity SVEM formula, so that the Profiler only includes prediction formulas linked to factors. With the option "Expand Intermediate Formulas" checked with this simplified formula, it should work :

Please find attached your datatable with the added simplified SVEM formula column and a script with the final Profiler.

Re: SVEM Prediction formula

frankderuyck — Mon, 08 Dec 2025 14:51:33 GMT

Victor, is what I do below right?

When I click OK that's what I get again..

Re: SVEM Prediction formula

Victor_G — Mon, 08 Dec 2025 15:06:41 GMT

Hi @frankderuyck,

Yes it's correct, please read my previous answer. I explained why you get some Prediction sample formula in the Profiler : some of these Prediction Formula are constant values, so JMP can't reduce it anymore, so they are part of the Profiler. If you replace the Prediction sample formula which have constant values by the constant values directly in the Pred SVEM formula, you won't have them in the Profiler.

I already did this with your table and prepared a script in your dataset with the correct and expected Profiler.

Re: SVEM Prediction formula

frankderuyck — Mon, 08 Dec 2025 18:18:40 GMT

OK Victor, pity so complex, why not possible to easilysave the simplified formula like the other prediction formulas? This is not easy to teach to trainees..

Re: SVEM Prediction formula

Victor_G — Mon, 08 Dec 2025 21:42:51 GMT

If you intend to use this example for teaching, I would consider using a more simple example where the distribution type can be Normal ; this way, you can directly save the SVEM prediction formula and you won't need the individual resample formulas.