A Method for Constructing Valid Restricted Randomization Schemes Using the Theory ofD-Optimal Design of Experiments
Journal of the Royal Statistical Society: Series B (Statistical Methodology) · 1981 · Volume 43 · Issue 2
DOI: 10.1111/j.2517-6161.1981.tb01166.x
Abstract
Complete randomization of a one-way layout design may lead to problems if the resulting choice of layout is considered unsuitable by the experimenter. Valid restricted randomization is an attempt to retain the mathematical properties of complete randomization while ensuring that the probability of selection of an unsuitable layout is zero. The problem of constructing valid restricted randomization schemes, when these exist, is shown to be equivalent to a particular problem in the theory of optimal design of experiments.
Keywords
one-way layout, optimal design of experiments, randomization, restricted randomization
Enable JavaScript for citation tools and additional paper interactions.