Simple Markov models are fitted to a small sample of longitudinal categorical data of teachers' ratings of children's classroom behavior. Although the data consist only of observations at five occasions, it was possible, after dividing the data into two groups, to fit plausible models in continuous time. (Author/BW)

Two stage multiple-comparison procedures give an exact solution to problems of power and Type I errors, but require equal sample sizes in the first stage. This paper suggests a method of evaluating the experimentwise Type I error probability when the first stage has unequal sample sizes. (Author/BW)

Cut-and-try techniques that point to appropriate transformations of variables and to the selection of sets of variables for an equation that may improve understanding of a social process are illustrated. (MV)

Two related problems are discussed: developing a methodology which (1) will not require full commitment of a local education agency to new techniques which may be ineffective in local settings and (2) will allow graceful abandonment of a new technology that may be proved ineffective. An example is discussed. (CTM)

Natural statistical models based on renewal processes for individuals' Behavior Stream are developed. For continuous observation, statistical and psychometric properties are obtained for empirical: (1) rates of behavior; (2) proportions of behavior type; (3) prevalence; and (4) event duration. Results provide a guide for design and analysis. (SLD)

Some unresolved methodological and philosophical issues in the assessment of performance trends are discussed as they relate to the National Assessment of Educational Progress (NAEP). How to measure performance change while remaining responsive to advances in curriculum and the technology of assessment is a central dilemma. (SLD)