作者: O. Kempthorne , G. Zyskind
DOI:
关键词:
摘要: Abstract : Research on analysis of variance procedures is described. A new series orthogonal maineffect plans presented, allowing for the testing (2(s to nth power -1)/(S-1)) factors each at s levels in 2 observations and two classes main-effect with unequal numbers levels. Previous work extended by developing general rules structure expectations mean squares balanced samples from populations which involve nesting crossingAND RANDOM CONFOUNDING. Results research are given one class partially structures, symmetric Latin cube. Early results made an attempt obtain a formulation based partitions. The role covariance structures induced randomization relevance these use least considered. Some initial tests preliminary constrained given. (Author)