Model Browser User's Guide

Design of Experiment Tutorial

Structure of This Design Editor Tutorial

The following sections guide you through constructing optimal, classical, and space-filling designs; how to compare designs using the prediction error variance (PEV) viewer and Design Evaluation tool; and how to apply constraints to designs.

1. The first section introduces the concept of design of experiment, and outlines the advantages of good experimental design for mapping modern engines. Then there is a description of the design styles available in the Model-Based Calibration Toolbox.
• What Is Design of Experiment?
• Design Styles
2. To start the tutorial you pick a model to design an experiment for, enter the Design Editor, and construct an optimal design. Once you create a design, you can use the displays and tools to examine the properties of the design, save the design, and make changes.

1. See
   • Starting the Design Editor
   • Optimal Designs
   • Design Displays
   • Prediction Error Variance Viewer
   • Saving Designs
   • Improving the Design

3. Next you create a classical design, and use the PEV viewer to compare it with the previous design. You can also use the Design Evaluation tool to view all details of any design; it is introduced in this example.

1. See
   • Classical Designs
   • Design Evaluation Tool

4. Lastly you construct a space-filling design and compare it with the others using the PEV viewer. Then you construct and apply two different constraints to this design and view the results. Normally you would design constraints before constructing a design, but for the purposes of this tutorial you make constraints last so you can view the effects on your design.

1. See
   • Space-Filling Designs
   • Applying Constraints

For more details on functionality in the Design Editor, see The Design Editor.

Exporting the Model

What Is Design of Experiment?