Design of Experiments Guide > Response Surface Designs
Publication date: 04/12/2021

Response Surface Designs

Response surface designs are useful for modeling quadratic surfaces. A response surface model can identify a point where a minimum or maximum value of the response occurs, if one exists inside the design region. Three distinct values for each factor are necessary to fit a quadratic function, so standard two-level designs are not appropriate for fitting curved surfaces.

Response surface designs are capable of fitting a second-order prediction equation for the response. The quadratic terms in these equations model the curvature in the true response function. If a maximum or minimum exists inside the design region, the point where that value occurs can be estimated.

Figure 11.1 Model for Response Surface Design ResultsĀ 

Model for Response Surface Design Results


Overview of Response Surface Designs

Example of a Response Surface Design

Construct a Box-Behnken Design
Analyze the Experimental Data
Explore Optimal Settings

Response Surface Design Window

Choose a Design
Specify Output Options
Make Table

Response Surface Design Options

Want more information? Have questions? Get answers in the JMP User Community (