Issues regarding confidence and tolerance intervals are discussed within the context of educational measurement. Conceptual distinctions are drawn between these two types of intervals; and examples, under various error and true score models, are used to compare such intervals. It is shown that there tend to be only small differences in tolerance…

The purpose of this paper is to demonstrate in detail how the Empirical Bayes (EB) statistical estimation strategy can be applied to an important class of educational research contexts. EB methods are tailored specifically to the analysis of data with a hierarchical structure. For instance, investigators may be interested in discovering how…

Lord's Paradox is analyzed in terms of a simple mathematical model for causal inference. The resolution of Lord's Paradox from this perspective has two aspects. First, the descriptive, non-causal conclusions of the two hypothetical statisticians are both correct. They appear contradictory only because they describe quite different aspects of the…

Provides a set of guidelines for evaluating research using structural equation modeling (SEM). Offers insight into how someone familiar with SEM would judge the adequacy of a study using such methods. (Author/RH)

This study identified the most productive reviewing journals for newly published business management titles. Two assumptions were shown to be supported by the data: a small core of journals carry the greatest number of reviews and a few monographs are reviewed repeatedly but the majority rarely or not at all. (Author/EM)

This study determined through psychophysical comparison of scaling data that speech naturalness judgments of stutterers and nonstutterers from audiovisual recordings form a metathetic (or qualitative) rather than prothetic (or quantitative) continuum. Both direct magnitude estimation and equal-appearing interval scaling were valid, but interval…

With the exception of the procedures developed by Porter and colleagues (Porter, 2002), other methods of defining and measuring alignment are essentially limited to alignment between tests and standards. Porter's procedures have been generalized to investigating the alignment between content standards, tests, textbooks, and even classroom…

In his early exposition of path analysis, Duncan (1966) noted that the method "provides a calculus for indirect effects." Despite the interest in indirect causal effects, most users treat them as if they are population parameters and do not test whether they are statistically significant. Sobel (1982) has recently derived the asymptotic…

The article describes procedures employed for the quantitative synthesis of single-subject research literature in special education. The need for objective, systematic review procedures is noted; previous approaches are reviewed; and the authors' approach (which makes use of overlapping data across phases as an outcome metric) is outlined.…

An evaluation of the "Percentage of Nonoverlapping Data" approach for quantifying outcomes of single-subject research in special education reveals that it is potentially too sensitive to atypical baseline data, not powerful enough to discriminate important treatment differences, and adversely affected by even subtle trends in the data.…

The response to a critique of a proposed method of quantifying outcomes of single-subject research in special education suggests that the alternative procedure proposed has theoretical but not practical merit due to the limited number of observations typically found in single-subject baselines. (Author/DB)

The method of using the percentage of nonoverlapping data points to summarize and synthesize single-subject research in special education was applied to six specific studies. The method was found lacking for such reasons as its failure to identify patterns across time or vital idiosyncrasies in behavior within and across studies. (Author/DB)

The response to a critique of a proposed method of quantitatively synthesizing single subject research in special education reaffirms the authors' view that narrative review procedures are of limited utility without objective standards for evaluating study outcomes. (DB)

In response to Hallahan et al, the authors suggest that variability in prevalence is a function of the methods used to examine prevalence differences and that the effect specific discrepancy criteria for learning disabilities have on the number of students identified is the critical issue. (Author/DB)

Demonstrates ways in which conclusions about models may be affected by violations of the assumption that the observed variables are normally distributed. Addresses the issue of the robustness of findings obtained under such conditions. (Author/RH)