Randomization tests are often recommended when parametric assumptions may be violated because they require no distributional or random sampling assumptions in order to be valid. In addition to being exact, a randomization test may also be more powerful than its parametric counterpart. This was demonstrated in a simulation study which examined the…

Test of homogeneity of covariances (or homoscedasticity) among several groups has many applications in statistical analysis. In the context of incomplete data analysis, tests of homoscedasticity among groups of cases with identical missing data patterns have been proposed to test whether data are missing completely at random (MCAR). These tests of…

The infinitesimal jackknife provides a simple general method for estimating standard errors in covariance structure analysis. Beyond its simplicity and generality what makes the infinitesimal jackknife method attractive is that essentially no assumptions are required to produce consistent standard error estimates, not even the requirement that the…

In the signal detection paradigm, the non-parametric index of sensitivity A', as first introduced by Pollack and Norman (1964), is a popular alternative to the more traditional d' measure of sensitivity. Smith (1995) clarified a confusion about the interpretation of A' in relation to the area beneath proper receiver operating characteristic (ROC)…

A general method of devising stepwise multiple testing procedures with fixed experimentwise error is applied to the problem of non-parametric randomized block design with ordered alternatives. In addition, the method is applied to other models with ordered alternatives. (Author)

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)

A method is developed for estimating the response time distribution of an unobserved component in a two-component serial model. The estimate of the component's density function is constrained to be only unimodal and non-negative. Numerical examples suggest the method can yield reasonably accurate estimates with sample sizes of 300. (Author/CTM)

A monotone invariant method of hierarchical clustering based on the Mann-Whitney U-statistic is presented. The effectiveness of the complete-link, single-link, and U-statistic methods are evaluated. The U-statistic method is found to be consistently more effective in recovering the original tree structures than the alternative methods. (Author/JKS)

A new measure of correlation and a measure of scale are proposed which are substantially more robust than their least squares counterparts. Increased robustness may also be obtained by use of equal regression weights, or knowledge of the theoretical structure of the weights. (Author/HG)

The problem of objectively comparing two independently determined partitions of N objects or variables is discussed. A similarity measure based on the simple matching coefficient is defined and related to previously suggested measures. (Author/JKS)

The equivalence between non-parametric marginal logistic models (NMLMs) and a class of discrete marginal logistic models is examined. Parametric models offer some of the advantages of the NMLMs approach, but there are more restrictions on the manifest probabilities. (SLD)

Three dimensional contingency tables in which one variable is considered to be a factor and the other two variables have a natural relationship (such as left and right eye vision) are analyzed. Models involving symmetry and proportional symmetry between the related variables are also presented. (Author/JKS)

The Lorge-Solomon approach to group problem solving situations and its extensions to trichotomous response situations are examined by use of the maximum likelihood methods. (DG)