Answers are grounded in this paper and cite their sources.
Sufficient combinatorial conditions for weak and strong validity of randomization are well known for some common classes of designs with single error strata. These conditions are generalized to orthogonal designs with multiple error strata given by an association scheme on the plots and with a treatment decomposition also defined by an association scheme.
No takes yet. Share an insight, caveat, or question.
Bailey et al. (1987) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: