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.
Get the free JMP Student Edition for qualified students and instructors at degree granting institutions.
Choose Language Hide Translation Bar
View Original Published Thread

What my factors are divided for?

DeepMarmot38570
Level I

Hello,

I'm new in the world of DoE. I noticed that all my factors are divided by 0.23 but I really can't understand what that number means.

Can someone help me? Thank you

1 ACCEPTED SOLUTION

Accepted Solutions
Victor_G
Super User


Re: What my factors are divided for?

Hi @DeepMarmot38570,

 

Welcome in the Community (and in the mystical realm of DoE) !

 

What you see is variable Coding in DoE : Your factors may have very different ranges that could influence the regression analysis and results. In order to avoid unfair or difficult comparison of the factors influenced by their ranges (and units), there is a variable coding done in the DoE, so that any max value for every factor is coded as 1 and the min values are coded as -1. This enable to have a fair assessment and comparison between factors during analysis (you can see this coding in the column property "Coding" of your factors).

 

In order to realize this coding, continuous factors are centered by the mean, and scaled by the range/2 : Low and High Coded Values

You can see here an example of variable coding for DoE : Example of Coded DOE Factors

 

I hope this answer will help you,

 

Victor GUILLER

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

View solution in original post

1 REPLY 1
Victor_G
Super User


Re: What my factors are divided for?

Hi @DeepMarmot38570,

 

Welcome in the Community (and in the mystical realm of DoE) !

 

What you see is variable Coding in DoE : Your factors may have very different ranges that could influence the regression analysis and results. In order to avoid unfair or difficult comparison of the factors influenced by their ranges (and units), there is a variable coding done in the DoE, so that any max value for every factor is coded as 1 and the min values are coded as -1. This enable to have a fair assessment and comparison between factors during analysis (you can see this coding in the column property "Coding" of your factors).

 

In order to realize this coding, continuous factors are centered by the mean, and scaled by the range/2 : Low and High Coded Values

You can see here an example of variable coding for DoE : Example of Coded DOE Factors

 

I hope this answer will help you,

 

Victor GUILLER

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