A content analysis of 10,279 dissertation abstracts in education from 1950 to 1990 shows that the descriptive design, predominantly in surveys, has dominated. Almost one-fourth of the dissertations used no statistics, and almost one-third failed to find statistically significant results. Few changes are apparent over the years. (SLD)

Research (Goodman, Fulbright, & Zimmerman, 1997; IEL, 2001) supports that the most critical decision a school board has to make is its selection and appointment of a superintendent to lead the district toward its mission of effective schooling for all students. Given that board members hold influential power in this regard, what competencies…

The capability was studied of each of three models for producing indices that will reproduce school effectiveness rankings established a priori through simulation. The models used were a within-group regression technique, a regression model using individual scores, and a regression model using means. Data for 54 hypothetical schools on input, SES,…

A Monte Carlo technique was used to investigate the small sample goodness of fit and statistical power of several nonparametric tests and their parametric analogues when applied to data which violate parametric assumptions. The motivation was to facilitate choice among three designs, simple random assignment with and without a concomitant variable…

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)

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…

Given that academics know about the current ecological condition of the planet and about the sustainable use of the natural resources, there is an obligation for universities to become leaders in the movement to prevent global ecological collapse. Thus, determining opinions of university students in Turkey on the general awareness of sustainable…

This study guide presents lessons on hand calculating various statistics: Central Tendency and Dispersion; Tips on Data Presentation; Two-Tailed and One-Tailed Tests of Significance; Error Types; Standard Scores; Non-Parametric Tests such as Chi-square, Spearman Rho, Sign Test, Wilcoxon Matched Pairs, Mann-Whitney U, Kruskal-Wallis, and Rank Sums;…

The use of stepwise regression has been criticized for both interpretive misunderstandings and statistical aberrations. A major statistical problem with stepwise regression and other procedures that involve multiple significance tests is the inflation of the Type I error rate. General approaches to control the family-wise error rate such as the…

An essential first step in the investigation of employment discrimination is establishing that the selection procedure has had an adverse impact. The 80% rule and statistical significance (as determined with a chi-square test), two methods of assessing adverse impact, were compared considering the variables: number of applicants (N), proportion of…

The current state of usage of regression models in analysis of variance (ANOVA) designs is empirically examined, and examples of several statistical errors made in usage are presented. The assumptions of the general linear model are that all predictors are known without error of measurement and are fixed with no replication or sample variation; in…

A DISCUSSION WAS PRESENTED ON THE PROCEDURES OF EQUATING DIVERSE ABILITY SCORES OBTAINED BY DIFFERENT SCALED MEASURES. THE AUTHOR INDICATED THE NECESSITY OF EQUATING SUCH SCORES WHEN ABILITY IS TO BE TREATED AS A SINGLE INDEPENDENT VARIABLE IN SIGNIFICANCE TESTS AND IN COMPARATIVE ANALYSES OF DICHOTOMIZED GROUPS. A NEW RATIONALE FOR EQUATING…