- Contents
- Learn about JMP
- Introduction to DOE
- Starting Out with DOE
- Custom Designs
- Construct Designs That Meet Your Needs
- Overview of Custom Design
- Example of a Custom Design
- Custom Design Window
- Custom Design Options
- Technical Details
- Examples of Custom Designs
- Perform Experiments That Meet Your Needs
- Screening Experiments
- Response Surface Experiments
- Mixture Experiments
- Experiments with Covariates
- Experiments with Randomization Restrictions
- Augment Designs
- Definitive Screening Designs
- The Fit Definitive Screening Platform
- Screening Designs
- Overview of Screening Designs
- Examples of Screening Designs
- Screening Design Window
- Screening Design Options
- Additional Examples of Screening Designs
- The Fit Two Level Screening Platform
- Response Surface Designs
- Full Factorial Designs
- Mixture Designs
- Taguchi Designs
- Evaluate Designs
- Explore Properties of Your Design
- Overview of Evaluate Design
- Example of Evaluate Design
- Evaluate Design Launch Window
- Evaluate Design Window
- Evaluate Design Options
- Compare Designs
- Compare and Evaluate Designs Simultaneously
- Overview of Comparing Designs
- Examples of Comparing Designs
- Compare Designs Launch Window
- Compare Designs Window: Specify Model and Alias Terms
- Compare Designs Window: Design Evaluation
- Compare Designs Options
- Prospective Sample Size and Power
- Discrete Choice Designs
- MaxDiff Design
- Covering Arrays
- Space-Filling Designs
- Overview of Space-Filling Designs
- Space Filling Design Window
- Space Filling Design Options
- Sphere-Packing Designs
- Latin Hypercube Designs
- Uniform Designs
- Comparing Sphere-Packing, Latin Hypercube, and Uniform Methods
- Minimum Potential Designs
- Maximum Entropy Designs
- Gaussian Process IMSE Optimal Designs
- Fast Flexible Filling Designs
- Borehole Model: A Sphere-Packing Example
- Accelerated Life Test Designs
- Nonlinear Designs
- Column Properties
- Technical Details
- References
- Index
Chapter 15
Evaluate Designs
Explore Properties of Your Design
Using the Evaluate Design platform, you can:
• See the strengths and limitations of your existing experimental design.
• Determine your design’s ability to detect effects associated with meaningful changes in the response.
• Address prediction variance and the precision of your estimates.
• Gain insight on aliasing.
• Obtain efficiency measures.
The Evaluate Design platform generates the results that appear in the Design Evaluation outlines provided by several DOE platforms. Diagnostics provided by both Evaluate Design and the Design Evaluation outlines include the following:
• power analysis
• a prediction variance profiler and surface plot
• a fraction of design space plot, showing how much of the design space has prediction variance above a given value
• estimation efficiency measures for parameter estimates
• the alias matrix, showing the bias structure for model effects
• a color map showing absolute correlations among effects
• design efficiency values
Figure 15.1 Comparison of Two Fraction of Design Space Plots
-
No Comment
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.