Interaction Graphs: Graphical Aids for Planning Experiments

Abstract

Interaction graphs are graphical aids to plan fractional factorial experiments. A fractional factorial plan can be generated from an orthogonal array by selecting certain columns of the orthogonal array and deleting the rest. Interaction graphs are graphical aids for identifying the appropriate columns. They are most useful for planning two-level fractional factorial experiments that allow unconfounded estimation of all main effects and some specified interaction effects under the assumption that all unspecified interaction effects are negligible. Interaction graphs, unlike Taguchi's linear graphs, identify the confounding relationships associated with the fractional factorial plan. And, unlike most other methods for planning experiments that allow unconfounded estimation of all main effects and some specified interaction effects, interaction graphs do not require the knowledge of defining contrasts.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 57 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.