We study several combinatorial problems related to the choice of groups of subsets to be used in the subsampling procedure of Hartigan (J. Amer. Statist. Assoc. 1969). The complete separation property is shown to guarantee asymptotic efficiency relative to $t$. Problems associated with the relative variance criterion are discussed.
"Completely Separating Groups in Subsampling." Ann. Statist. 2 (3) 572 - 578, May, 1974. https://doi.org/10.1214/aos/1176342719