Computing, software and networks

Experiments here usually have about 2 factors and 18 runs. Full factorials and fractional factorials are the most common. The catalog holds only a few from this field so far.

Plan one like these

Full factorial
Fractional factorial or screening
Central composite or Box-Behnken
Other designs

Show the numbers

The experiments of each kind, with their median size
Kind of design	Experiments	Factors	Runs
Full factorial	1	2	8
Fractional factorial or screening	1	8	18
Central composite or Box-Behnken	1	4	43
Other designs	2	1.5	23

Factors and runs are the medians of each kind.

Full factorial

Every combination of the factor levels.

Web sales: free-shipping threshold and a required profile, run on eight TuesdaysDunn (2026) · 2 factors, 8 runs

Fractional factorial or screening

A planned part of the combinations, to find the factors that matter.

CPU time of a large program: seven system settings at three levels and one at two, in an 18-run D-optimal design, under three disk file schemesSchmidt and Launsby (2000) · 8 factors, 18 runs

Central composite or Box-Behnken

Extra runs that fit curvature, to find an optimum.

Simulated integrated computer network: mean packet delay, link utilization and calls blocked against four load and capacity inputsSchmidt and Launsby (2000) · 4 factors, 43 runs

Other designs

Optimal, blocked, split-plot and other designs made for the problem.