Treatment contrasts in paired comparisons: convergence of a basic iterative scheme for estimation

Abstract
In am earlier paper, the authors have presented the methodology for consideration of specified treatment contrasts in paired comparisons. An iterative method of solution of derived likelihood equations was given. This paper considers the iterative method. It is proved that, subject to a mild condition, the iterative scheme converges to a solution of the likelihood equations that is unique and yields the maximum of the likelihood function on a parameter space constrained by the condition that certain treatment contrasts are null.

This publication has 1 reference indexed in Scilit: