Fractional factorial design

A deliberately reduced subset of a full factorial design that still estimates main effects at a fraction of the traffic cost.

Instead of running every combination a full factorial design would require, a fractional factorial design runs a carefully chosen subset that still estimates main effects — and sometimes low-order interactions — at a fraction of the traffic cost. The price is assuming some higher-order interactions are negligible, which is usually a safe bet once you're past two or three factors.

It's the right middle path when you have more factors you care about than you have six-figure-per-page traffic to spend on the full cross-product. TraqLyte names this strategy in its assignment-strategy vocabulary as planned; as of this writing it isn't implemented yet, so campaigns needing it should run full-factorial or sequential A/B in the meantime.