nav[aria-label="Primary Navigation"] { padding: 0; & ul { list-style: none; width: 100%; display: flex; flex-direction: row; justify-content: start; align-items: start; gap: 30px; padding: 0; & li { margin: 0; } & ul li { list-style: none; } } }

4590_en-US

liliconcom

Is it possible to specify how JMP scales the inputs to a poly model?

In JMP, you can show coefficients scaled or unscaled. Scaled estimates for continuous factors centered by mean and scaled by range/2. e.g.

Scaled Estimates

Intercept 0.203939834

Engine Speed 1.384267713

Fuel Quantity 2.6370936744

MAF -1.925946311

Boost Pressure 1.317416246

(Engine Speed-1624.42)*(Fuel Quantity-59.324) 1.1419551545

(Fuel Quantity-59.324)*(Fuel Quantity-59.324) 0.0275770938

(Fuel Quantity-59.324)*(Boost Pressure-155.281) -1.255525253

For reasons of convention I would like to scale by the mean of the design bounds not the mean of all the tested settings. Is it possible to change the scaling options in JMP?

Incidentally, in the Scaled Estimates display, why are main effects not shown minus mean whereas interaction terms are? I assume the main effects are scaled too.