This study was concerned with various schemes for reducing the number of variables in a multivariate analysis. Two sets of illustrative data were used; the numbers of criterion groups were 3 and 5. The proportion of correct classifications was employed as an index of discriminatory power of each subset of variables selected. Of the four procedures…

The Head Start data analyzed by Magidson (1977) were reanalyzed using Joreskog's (1976) LISREL computer program methodology. The hypothesis that the Head Start program produced zero effects on the cognitive abilities of its participants was evaluated by several Chi Square tests. In all cases, the null hypothesis could not be rejected. (Author/CTM)

In a reply to the previous article (TM 503 435), Magidson disparages the arbitrary application of the .05 significance level to these data, responds to several assertions, and provides additional data in support of his original article showing positive effects for Project Head Start. (CTM)

Two easily computed test statistics are proposed for testing the equality of two correlated proportions when some observations are missing on both responses. The performance of these tests in terms of size and power is compared with other tests by means of Monte Carlo simulations. (Author/BS)

Contends that erroneous conclusions concerning intraindividual strengths may result when comparing scaled scores on subtests of The Test of Reading Comprehension. Examination of scaled scores may seem to indicate that a given student has performed better on one subtest than on another when the difference between the two scores is not statistically…

Explores response time variations in National Library of Medicine's ELHILL bibliographic search system and analyzes statistical significance of response time in terms of its variations by day of week, hour of day, particular bibliographic file being searched, command issued by user, number of users logged onto system. Ten references are cited.…

A Type VI error results from inconsistency between the researchers' question of interest and the statistical procedures employed to analyze the data. An example of a research problem is analyzed to show the increase in statistical power resulting from improved research design, using multiple regression instead of analysis of variance. (CTM)

An experiment randomly assigned youth workers to a training or a control group and measured the effectiveness of the training by a questionnaire given to both groups. Results of the questionnaire were related to content analysis of the training sessions, which differed in some respects from the intended content. (CTM)

In describing several pitfalls associated with research on school and teacher effectiveness, the following aspects of effectiveness research are considered: correlation-causation relationship, controlling for background factors, statistical and practical significance, instrumentation problems, regression effects, measurement of change, nonlinear…

Discusses the potential for increasing library effectiveness through the appropriate design and utilization of research and describes fundamental research and statistical techniques. Topics examined include areas amenable to data collection, data collection methods amenable to statistical analysis, measurement techniques and levels of…

The degree to which reliability affects the power of analysis of variance (ANOVA) tests involving one factor with two and three samples was quantified and tabulated by taking into account sample size, level of significance, and true score effect size. Results confirm a substantial effect on power. (SLD)

Journal editors respond to criticisms of reliance on statistical significance in research reporting. Joel R. Levin ("Journal of Educational Psychology") defends its use, whereas William D. Schafer ("Measurement and Evaluation in Counseling and Development") emphasizes the distinction between statistically significant and important. William Asher…

This article reports a study of the learning environments in computer networked classrooms. The study is unique in that it involved an evaluation of both the physical and psychosocial classroom environments in these computerised settings through the use of a combination of questionnaires and ergonomic evaluations. The study involved administering…

This study examines the influences of learners' characteristics on the development of computer self-efficacy using the GOMS (goal, operators, methods, and selection rules) model. Students' learning style, prior computer course experience, and computer self-efficacy were measured in the pretest, and computer self-efficacy was measured in the…

Severe reductions in funding coupled with the imperative to measure and report teachers' ability to integrate technology into their practice pose a significant problem for school districts in New Jersey. This study was designed to identify factors that influence teacher use of technology. A review of the literature identified four areas of…