Let ∑x be the (population) dispersion matrix, assumed well-estimated, of a set of non-homogeneous item scores. Finding the greatest lower bound for the reliability of the total of these scores is shown to be equivalent to minimizing the trace of ∑x by reducing the diagonal elements while keeping the matrix non-negative definite. Using this approach, Guttman's bounds are reviewed, a method is established to determine whether his λ4 (maximum split-half coefficient alpha) is the greatest lower bound in any instance, and three new bounds are discussed. A geometric representation, which sheds light on many of the bounds, is described.

Finding the greatest lower bound for the reliability of the total score on a test comprising n non-homogenous items with dispersion matrix Σx is equivalent to maximizing the trace of a diagonal matrix ΣE with elements θI, subject to ΣE and ΣT=Σx − ΣE being non-negative definite. The cases n=2 and n=3 are solved explicity. A computer search in the space of the θi is developed for the general case. When Guttman's λ4 (maximum split-half coefficient alpha) is not the g.l.b., the maximizing set of θi makes the rank of ΣT less than n − 1. Numerical examples of various bounds are given.