Kruskal has proposed two modifications of monotone regression that can be applied if there are ties in nonmetric scaling data. In this note Kruskal's conjecture that his algorithms give the optimal least squares solution of these modified monotone regression problems is proven. Also, an additional approach is proposed. (Author/JKS)

A measure of multiple rank correlation is proposed for the situation of no tied observations in the variables. The measure is a weighted average of two squared Kendall taus. The measure is equivalent to one proposed by Moran. (Author/JKS)

A unified approach, based on ranks, to the statistical analysis of data arising from complex experimental designs is presented. The rank methods closely parallel the familiar methods of least squares, so that the estimates and tests have natural interpretations. (Author/JKS)

The monotone regression function of Kruskal and the rank image of Guttman and Lingoes are fitted to bivariate normal samples and their statistical properties contrasted. Tables of results are presented. (Author/JKS)

A method to provide estimates of parameters of specified nonlinear equations from ordinal data generated from a crossed design is presented. The statistical basis for the method, called NOPE (nonmetric parameter estimation), as well as examples using artifical data, are presented. (Author/JKS)