Community Trekker

Joined:

Jul 15, 2014

Difference between Response Surface and 3 level full factorial

Hi All,

Anyone have any link that is able to explain the difference between the two DOE methods above?

Rgrds

Irfan

1 ACCEPTED SOLUTION

Accepted Solutions

Staff

Joined:

Jun 23, 2011

Solution

Re: Difference between Response Surface and 3 level full factorial

Both of these design methods produce runs with three levels for each factor. The full factorial, of course, produces all combinations of factor levels. The response surface methods (e.g., Box-Behnken or Box-Wilson) do not. The Box-Behken is more economical for the typical optimization situation involving only a few factors (after screening) but does not share any runs with the two-level screening designs. The Box-Wilson designs are also called the central composite designs because they are composed of a two-level factorial design, axial points, and center points.

You can probably do better (smaller prediction standard errors from fewer runs) with a custom design for I-optimality than either of the older response surface methods.

I recommend:

• that you read the JMP guide by selecting Help > Books > Design of Experiments
• that you read "Optimal Design of Experiments," by Goos and Jones.
Learn it once, use it forever!

Staff

Joined:

Jun 23, 2011

Solution

Re: Difference between Response Surface and 3 level full factorial

Both of these design methods produce runs with three levels for each factor. The full factorial, of course, produces all combinations of factor levels. The response surface methods (e.g., Box-Behnken or Box-Wilson) do not. The Box-Behken is more economical for the typical optimization situation involving only a few factors (after screening) but does not share any runs with the two-level screening designs. The Box-Wilson designs are also called the central composite designs because they are composed of a two-level factorial design, axial points, and center points.

You can probably do better (smaller prediction standard errors from fewer runs) with a custom design for I-optimality than either of the older response surface methods.

I recommend:

• that you read the JMP guide by selecting Help > Books > Design of Experiments
• that you read "Optimal Design of Experiments," by Goos and Jones.
Learn it once, use it forever!