Demonstrates the structure of factorial designs in identifying experimental strata and enhancing predictions.
This study demonstrates formal connections between Abelian group theory and factorial experimental designs. I begin by showing that full-factorial designs are isomorphic to elementary p-groups. I continue with an analysis of the general group and subgroup structure of 3 × 3 full-factorial designs commonly utilized in detection studies, followed by extensions to more general but related designs in the subsequent section, namely, 3 × 3 × 3 designs. I show that the subgroup lattice of 3 × 3 designs decompose the experiment into single and double-target subgroups and a target-absent subgroup. An application of this endeavor is the identification of experimental strata, interactions, interaction contrasts, and fractional designs. By using examples from the reaction-time (RT) and non-parametric modeling literature, it is shown how comparisons across and within these subgroup structures can readily be used to derive predictions about human information processing. Relatedly, I provide predictions derived from subgroup analyses to increase statistical power and simplify data analyses. Finally, some suggestions are provided for analyzing more general designs.
No takes yet. Share an insight, caveat, or question.
Nicholas Altieri (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:
More from Frontiers in Psychology