The problem of determing how many significant discriminant functions are present in a given data set for a one-way, fixed-effects multivariate analysis of variance design is studied using a Monte Carlo procedure. A variety of procedures, including the popular partitioned-U procedure, are compared with respect to their Type I error rates and power…

A correction of the standard F-ratio for unreliability of the dependent measure has recently been proposed by Winne; the rationale is analogous to that of correcting a correlation for attenuation. However, there are two problems associated with Winne's correction of which potential users should be aware. First, the corrected statistic, F*, has…

Part and bi-partial canonical correlations were developed by extending the definitions of part and bi-partial correlation to sets of variates. These coefficients may be used to help researchers explore relationships which exist among several sets of normally distributed variates. (Author)

A major factor in the failure to successfully implement an innovation such as team teaching, is the absence of a mechanism to identify and treat difficulties arising from the effort to implement the innovation. The hypothesis was tested that teachers who are ambivalent toward team teaching and teachers who experience frustration in attempting to…

This report presents the procedures, results, and conclusions of a study designed to compare the achievement in beginning college physics of students completing PSSC high school physics with students completing a traditional high school physics course. Factors of ability and achievement were held constant while scores on the criterion of marks in…

To test the hypothesis that learning depends on the influence and interaction of three primary variables--instruction, learner aptitude, and learning environment--an explanatory model was tested during the 1967-68 school year in an experiment conducted with the cooperation of a simple random sample of 56 teachers drawn from the National Science…

Three critical issues in the design and analysis of evaluation studies suggested at the conference are (1) the univariate versus multivariate dependent variable studies, (2) the choice of a response surface design over the conventional fixed model, and (3) the tendency to interpret every study as if it were being done for the first time. Taking…

To study the relationship of education to economic growth for the state of Iowa, the hypothesis that increasing the level of education for the labor force would lead to higher levels of income or economic growth was tested for the period from 1950-1967. The Cobb-Douglas production was used to evaluate the relationship. The function used labor…

A comparison was made of short- and long-term visual and auditory memory in relation to visual and auditory interference. The questions investigated were: (1) will interference be greater when it occurs in the same modality (auditory or visual) in which it was learned (i.e., similarity hypothesis), or (2) will interference be greater when it…

An equation was derived to determine the relationship between the pooled within-subgroup r (correlation coefficient) and the r obtained from the total group data. It was, thus, possible to assess the amount of distortion introduced by pooling heterogeneous subgroups. As a basis for deciding whether to pool two subgroups in order to calculate a…

One aspect of reference group theory, racial identification, was studied, and the effects of this identification on the acquisition of knowledge and the formation of attitudes were examined. Three hypotheses were investigated: (1) Children who perceive an instructional tape narrator to be a member of their own race will score significantly higher…

A set of mathematical consistencies that forms conditions of inequality in a theorem is summarized, and a strategy for its application with real data is presented. The theorem and strategy are suggested for immediate use by the practitioner seeking cause-effect relationships in a system of variables to cut down guess work and time in analysis and…

A computer-based learning simulation was developed at Florida State University which allows for high interactive responding via a time-sharing terminal for the purpose of demonstrating descriptive and inferential statistics. The statistical simulation (STATSIM) is comprised of four modules--chi square, t, z, and F distribution--and elucidates the…