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; } } }

63270_en-US

liliconcom

Functionality for highly correlated predictors to avoid extrapolation

Constraint Profiler: For highly correlated predictors, we are constructing constraints by using Hotelling T2 and DModX and adding them as prediction formulas to the Profiler. I know that P&G QS people already developed something similar for PLS models. Can JMP should provide a kind of built in functionality for all models with highly correlated predictors to avoid extrapolation?

Scripting

Statistics and Analytics

Re: Functionality for highly correlated predictors to avoid extrapolation - Status changed to: Delivered

Hi @reese_sj The profiler extrapolation in JMP 16 should solve this.

Comments

There are no comments yet

Quick Links

All Categories
Recent Posts
Activity
Unanswered
Groups
Help
Best Of