Developed by Ronald A. Fisher (The Design of Experiments, 1935) and carried into industry by George E. P. Box, William G. Hunter, and J. Stuart Hunter (Statistics for Experimenters, 1978).
Varies several factors together in a structured pattern, with replication and randomization, to learn in few runs how each factor and their interactions move an outcome.
When to reach for it
When several factors may affect a result, as in a process, a campaign, or a product setting, and testing one at a time would take too long.
How it runs
- Name the outcome to learn about.
- List the factors likely to affect it.
- Choose two or three levels per factor.
- Pick a design: full factorial, fractional, or screening.
- Plan replication, randomize the run order, and block similar units.
- Run it, then estimate main effects and interactions.
Where it sits in SOLVE eX
Go to the source
- The Design of Experiments, 1935
- Statistics for Experimenters, 1978