When treatments are administered in groups, clients interact in ways that lead to violations of a key assumption of most statistical analyses-the assumption of independence of observations. The resulting dependencies, when not properly accounted for, can increase Type I errors dramatically. Of the 33 studies of group-administered treatment on the…

P. A. Frazier, A. P. Tix, and K. E. Barron (2004) highlighted a normal theory method popularized by R. M. Baron and D. A. Kenny (1986) for testing the statistical significance of indirect effects (i.e., mediator variables) in multiple regression contexts. However, simulation studies suggest that this method lacks statistical power relative to some…

It is hypothesized that the use of an empirical indicator of a theoretical construct implies certain epistemic assumptions about the nature of the construct. In this study, the implications of assuming interval level of measurement using various isomorphic monotonically increasing epistemic alternatives to a commonly used occupational status index…

Gas flow patterns at a sampling nozzle are described in this presentation for the 12th Conference on Methods in Air Pollution and Industrial Hygiene Studies, University of Southern California, April, 1971. Three situations for sampling velocity are illustrated and analyzed, where the flow upstream of a sampling probe is: (1) equal to free stream…

Reports a class exercise which requires students to recalculate the Chi-squares, t-tests, and one-way ANOVAs found in published psychological research articles. Describes students' reaction to the exercise and provides data on the 13% error rate they discovered. (Author/JDH)

An analysis of 41 recently published articles in the "American Journal on Mental Retardation" and the "Journal of Mental Deficiency Research" found a higher than expected probability of Type I research errors, suggesting that approximately 20 percent of the statistically significant results may be erroneous. (DB)

Many of the currently available statistical indexes to detect answer copying lack sufficient power at small [alpha] levels or when the amount of copying is relatively small. Furthermore, there is no one index that is uniformly best. Depending on the type or amount of copying, certain indexes are better than others. The purpose of this article was…

This report describes efforts made in 1981-82 to develop an error-prone model (EPM) to help judge the extent of misreporting of income and family size on applications for government-sponsored school meal benefits. (EPM's are statistical formulas that produce scoring systems used to distinguish applications likely to result in excess benefits from…

Specific examples of the most common types of errors are cited. (RS)

For two random variables, X and Y, let D = X - Y, and let theta[subscript x], theta[subscript y], and theta[subscript d] be the corresponding medians. It is known that the Wilcoxon-Mann-Whitney test and its modern extensions do not test H[subscript o] : theta[subscript x] = theta[subscript y], but rather, they test H[subscript o] : theta[subscript…

One aspect of multiple regression--the shrinkage of the multiple correlation coefficient on cross-validation is reviewed. The paper consists of four sections. In section one, the distinction between a fixed and a random multiple regression model is made explicit. In section two, the cross-validation paradigm and an explanation for the occurrence…

The properties of four different tests of the treatment effect in experiments using linguistic materials are examined. (Author/RM)

Research supported by a grant from the Public Health Service, National Institute of Mental Health. (DD)