To ensure that your results are valid, consider the following guidelines when you collect data, perform the analysis, and interpret your results.
- The candidate points must be a general full factorial, response surface, or mixture design
- The design columns in the worksheet comprise the candidate set of experimental runs.
- The criterion for selection is D-optimality
- D-optimality provides the most precise estimates of the effects. Many other considerations can influence your final choice of experimental runs, including available resources, the goal of your experiment, other measures of optimality, and the terms that you expect to fit.
- The size of the optimal design should be adequate
- The sample size and power should be desirable for a practically important effect size. A usual use for optimal designs is to decrease the number of experimental runs, but smaller sample sizes may not provide a design that can detect small effects with sufficient power.
- The design is optimal only for the terms that you specify during model selection
- A design that is D-optimal for one set of terms is not necessarily D-optimal for a different set of terms.
- The run order should be randomized for data collection
- After selection of the optimal design, the design is not in run order. To display the design in run order, use . If the run order column matches the standard order column, use to randomize the design.
