Hawkin's procedure for testing a sequence of observations for a shift in location could have applicability for assessing change within a single subject. Monte Carlo results suggest that Hawkins' procedure is robust with respect to moderate violations of its underlying assumptions of homogeneity of variance and normality. (Author/GDC)

Errors of misclassification and their effects on categorical data analysis are discussed. The chi-square test for equality of two proportions is examined in the context of errorful categorical data. The effects of such errors are illustrated. A correction procedure is developed and discussed. (Author/MH)

A Monte Carlo approach was used to examine bias in the estimation of indirect effects and their associated standard errors. Results illustrate the adverse effects of nonnormality on the accuracy of significance tests in latent variable models estimated using normal theory maximum likelihood statistics. (SLD)

Refutes Peter Mueser's criticisms of the author's position on formalistic research approaches. Restates that statistical significance is virtually useless. Claims mathematical economists take their intellectual positions from mathematics departments bringing irrelevant intellectual values into economics. (NL)

Describes two invariance tests, the jackknife procedure and Procrustean rotation, and applies them in a discriminant analysis for this heuristic study. Invariance testing helps to prevent overemphasis on findings of statistical significance and overgeneralization of a research result, and thus is gaining favor as an indicator of result importance.…

This paper argues that judgment-based assessment of data from multiply replicated single-subject or small-N studies should replace normative-based (p=less than 0.05) assessment of large-N research in the clinical sciences, and asserts that inferential statistics should be abandoned as a method of evaluating clinical research data. (Author/JDD)

A brief overview is provided of the Conger-Lipshitz approach to estimating the reliability of a profile or test battery. A computational example from a recent study shows how canonical reliability can be obtained through existing statistical software. (SLD)

Twenty-eight books published from 1910 to 1949, 19 books published from 1990 to 1992, and 5 multiple edition books were reviewed to examine the presentations of statistical testing, particularly coverage of the p-value and fixed-alpha approaches. Statistical testing itself is not at fault, but some textbook presentations, testing practices, and…

Some of the methods originally used to find relationships between reliability and power associated with a single measurement are extended to difference scores. Results, based on explicit power calculations, show that augmenting the reliability of measurement by reducing error score variance can make significance tests of difference more powerful.…

Two articles discuss the controversy about the relationship between reliability and the power of significance tests in response to the discussion of Donald W. Zimmerman, Richard H. Williams, and Bruno D. Zumbo. Lloyd G. Humphreys emphasizes the differences between what statisticians can do and constraints on researchers. Zimmerman, Williams, and…

Comments on discussions of statistical significance testing in this special issue, placing the articles in the context of contemporary research literature. Empirical evidence is cited that suggests that the American Psychological Association's policy of encouraging effect size reporting has had no appreciable effect on the research literature.…

Studied the attitudes of representatives of journals in education, sociology, and psychology through an electronic survey completed by 194 journal representatives. Results suggest that the majority of journals do not have written policies concerning the reporting of results from statistical significance testing, and most indicated that statistical…

In this study, we investigated possible context effects when students chose to defer items and answer those items later during a computerized test. In 4 primary school reading tests, 126 items were studied. Logistic regression analyses identified 4 items across 4 grade levels as statistically significant. However, follow-up analyses indicated that…

The purpose of this exploratory study was to investigate the relationship between functional communication and executive function ability in aphasia. Twenty-five participants with aphasia underwent examination with an extensive test battery including measures of functional communication, executive function ability, and language impairment.…

A new item parameter replication method is proposed for assessing the statistical significance of the noncompensatory differential item functioning (NCDIF) index associated with the differential functioning of items and tests framework. In this new method, a cutoff score for each item is determined by obtaining a (1-alpha ) percentile rank score…