On the construction of approximate multi-factor designs from given marginals using the iterative proportional fitting procedure (Q1094059): Difference between revisions

For multifactor designs based on linear models, the information matrix generally depends on a certain set of marginal tables created from the design itself. This note considers the problems of whether a set of marginal tables is consistent, in that a design exist that can yield them, and of calculating such a design when at least one does exist. The results are obtained by direct analogy with the problem of maximum likelihood estimation in loglinear models for categorical data.