Share your ideas for the JMP Scripting Unsession at Discovery Summit by September 17th. We hope to see you there!
Choose Language Hide Translation Bar
Highlighted
yuzawaomine
Level II

How to make 28 Run Five-Factor Central Composite Design

Hi all-I'm studying Split Plot Design.
There is a table 12. '28 Run Five-Factor Central Composite Design'
in 'Split-Plot Designs:What, Why, and How' by BRADLEY JONES, CHRISTOPHER J. NACHTSHEIM,

as Follows:

yuzawaomine_0-1585545418506.png

I would like to make this DOE table with JMP,
please advice me how to make this table by JMP.

 

Thanks a lot.

Aki

2 ACCEPTED SOLUTIONS

Accepted Solutions
Highlighted

Re: How to make 28 Run Five-Factor Central Composite Design

The central composite designs (CCD) are made by selecting DOE > Classical > Response Surface Designs. You define the responses and factors and then click Continue. You are presented with a list of designs including the CCD choices. These designs have a number of options such as the axial distance and the number of center points to affect the characteristics of the design. It is not a split plot design. You cannot define a factor to be hard-to-change. So you must decide the runs that are grouped together in whole plots by manually adding the whole plot data column after clicking Make Table. You must also modify the model to include the whole plot as a random effect.

 

Please see Help > JMP Documentation Library > Design of Experiments book > Chapter 11: Response Surface Designs for more information and examples.

 

I strongly urge you to consider using a custom design for the split-plot experiment.

Learn it once, use it forever!

View solution in original post

Highlighted
statman
Level VII

Re: How to make 28 Run Five-Factor Central Composite Design

View more...
Since you are studying split-plot designs, you might find "Split-plot designs for robust product experimentation", Box and Jones from the Journal of Applied Statistics, Vol. 19, No. 1, 1992 to be of great value!

View solution in original post

4 REPLIES 4
Highlighted

Re: How to make 28 Run Five-Factor Central Composite Design

The central composite designs (CCD) are made by selecting DOE > Classical > Response Surface Designs. You define the responses and factors and then click Continue. You are presented with a list of designs including the CCD choices. These designs have a number of options such as the axial distance and the number of center points to affect the characteristics of the design. It is not a split plot design. You cannot define a factor to be hard-to-change. So you must decide the runs that are grouped together in whole plots by manually adding the whole plot data column after clicking Make Table. You must also modify the model to include the whole plot as a random effect.

 

Please see Help > JMP Documentation Library > Design of Experiments book > Chapter 11: Response Surface Designs for more information and examples.

 

I strongly urge you to consider using a custom design for the split-plot experiment.

Learn it once, use it forever!

View solution in original post

Highlighted
yuzawaomine
Level II

Re: How to make 28 Run Five-Factor Central Composite Design

Hi Mark

 

Thank you for your help.

Aki

Highlighted
statman
Level VII

Re: How to make 28 Run Five-Factor Central Composite Design

View more...
Since you are studying split-plot designs, you might find "Split-plot designs for robust product experimentation", Box and Jones from the Journal of Applied Statistics, Vol. 19, No. 1, 1992 to be of great value!

View solution in original post

Highlighted
yuzawaomine
Level II

Re: How to make 28 Run Five-Factor Central Composite Design

Thank you for your info.

I will get this article.

 

Aki

Article Labels

    There are no labels assigned to this post.