Design of Experiments Guide > Examples of Custom Designs
Publication date: 07/08/2024

Examples of Custom Designs

Perform Experiments That Meet Your Needs

Use the Custom Design platform as your primary tool for constructing a wide range of experimental designs. You can construct a variety of design types and fine tune them to your specific experimental needs and resource budget.

Custom Design provides more options and control than the Screening, Response Surface, Full Factorial, and Mixture Design platforms. The designs that you construct are created specifically to meet your goals.

The flexible special-purpose designs that you can construct using Custom Design include:

Screening designs, including supersaturated screening designs

Response surface designs, including those with categorical factors

Mixture designs, including those with process factors, and mixture of mixture designs

Designs that include covariates or that are robust to linear time trends

Fixed and random block designs

Split-plot, split-split-plot, and two-way split-plot (strip-plot) designs

In this chapter you construct most of these design types within the Custom Design platform. In many cases, you also analyze the experimental results. For help with using the Custom Design platform, see Custom Designs.

Figure 5.1 Fraction of Design Space Plot 

Fraction of Design Space Plot

Contents

Examples of Screening Experiments

Design That Estimates Main Effects Only
Design That Estimates All Two-Factor Interactions
Design That Avoids Aliasing of Main Effects and Two-Factor Interactions
Supersaturated Screening Designs
Design for Fixed Blocks

Examples of Response Surface Experiments

Response Surface Design
Response Surface Design with Flexible Blocking
Comparison of a D-Optimal and an I-Optimal Response Surface Design
Response Surface Design With Constraints and Categorical Factor

Examples of Mixture Experiments

Mixture Design with Nonmixture Factors
Mixture of Mixtures Design

Experiments with Covariates

Design with Fixed Covariates
Design with Hard-to-Change Covariates
Design with a Linear Time Trend

Experiments with Randomization Restrictions

Split-Plot Experiment
Two-Way Split-Plot Experiment

Experiments for Robust Process and Product Design

Want more information? Have questions? Get answers in the JMP User Community (community.jmp.com).