What is design of experiments (DOE)?
Definition
Design of experiments (DOE) is a structured method for planning which tests or simulation runs to perform, so the results support valid, objective conclusions from as few runs as possible. It chooses the combinations of input factors to test, and is used to screen influential variables, fit response surfaces and train surrogate models.
Example
Before training a surrogate model, a team decides which simulations to run. A deterministic solver returns the same result for the same inputs, so repeating a run adds nothing; the design instead spreads the runs across the whole input space, for example with Latin hypercube sampling, so each costly run adds new information.
Sources
- NIST/SEMATECH e-Handbook of Statistical Methods, "What is experimental design?", itl.nist.gov
- Sacks, Welch, Mitchell, Wynn, "Design and Analysis of Computer Experiments," Statistical Science 4(4), 1989, projecteuclid.org