Points out that one flaw in statistical foundations of much reading research is that researchers neglect to consider whether their findings could be replicated using a different sample of materials. Also shows that many topics in reading research do not quite fit the model for the null hypothesis. (TO)

The present study contrasted the robustness of the WSD and the F test to heterogeneity of variances. (Author)

Problems in making inferences from a sample to a population and from one cohort to other cohorts are discussed. It is concluded that in most cases a longitudinal design using repeated measures is preferable to an independent samples design. (Author)

The approach to outcome research described here has the double merit of preserving individuality and permitting pooling of data for overall analysis of results. (Author)

The assumption that an examinee's response to an item is independent of the context in which it occurs is tested. (PR)

Despite the precautions in subject selection many of the usual sex differences appeared, including boys' higher level of aggression toward peers. (MH)

A previous article, EA 500 335, is criticized for claiming the applicability of the CRAM model without research documentation. (MF)

A formula for determining sample size, which originally appeared in 1960, has lacked a table for easy reference. This article supplies a graph of the function and a table of values which permits easy determination of the size of sample needed to be representative of a given population. (DG)