cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
The Discovery Summit 2025 Call for Content is open! Submit an abstract today to present at our premier analytics conference.
See how to use to use Text Explorer to glean valuable information from text data at April 25 webinar.
Choose Language Hide Translation Bar
View Original Published Thread

Cedrick1
Level II

How Can I get Adequat precision in JMP after analysis Box-benken design ?

1 REPLY 1
Victor_G
Super User


Re: DOE

Hi @Cedrick1,

 

The "Adequate Precision" as displayed in Stat-Ease doesn't seem not a default calculation in JMP : Stat-Ease » v22.0 » Adequate Precision

Victor_G_1-1737470596066.png


However, considering the simple formula, it's quite easy to do it in JMP (here with the dataset "Bounce Data" from JMP Sample Index) :

  1. Fit a model on the design points and save the number of terms in your model, and the number of points :
    Victor_G_3-1737470909285.png
  2. Extract residual mean square (from "Analysis of Variance" tab) :
    Victor_G_0-1737470529795.png
  3. Save Prediction formula on your table, and use "Distribution" platform to easily access min and max predicted values :
    Victor_G_2-1737470840786.png
  4. You can then calculate the Adequate Precision of your model (in my case on this very clean/"ideal" dataset, it is equal to 156).

 

It should be possible to script it and use the values from the model report to directly calculate it.

Hope this answer will help you in the meantime, 

Victor GUILLER

"It is not unusual for a well-designed experiment to analyze itself" (Box, Hunter and Hunter)