In 1881, Donald MacAlister posed a problem in the "Educational Times" that remains relevant today. The problem centers on the statistical evidence for the effectiveness of a treatment based on a comparison between two proportions. A brief historical sketch is followed by a discussion of two default Bayesian solutions, one based on a…

The proportion of agreement, G, and kappa indexes are shown to differ in how they correct for chance agreements between two observers. On the basis of the findings, it is suggested that no single agreement index is appropriate for all sets of data. (Author/BW)

The viability of the FORTRAN computer language and its relationship to other languages (such as PASCAL) were discussed. A library of C language and assembly language FORTRAN-callable subroutines, developed for the use of behavioral science researchers, was introduced. (Author/GDC)

The use of Bayes' estimates for proportions in the Law of Comparative Judgment is suggested to avoid sample proportions of zero and one. (Author)

Maximized correlation as an internal reliability estimate for tests with few items was investigated. An actual sampling distribution of maximum correlation--"r" max--was empirically derived from 100 samples of 50 cases each from Rorschach test data and compared with those of alpha and an odd/even split, using 2,020 Rorschach protocols.…

Post-hoc blocking and analysis of covariance (ANCOVA) both employ a concomitant variable to increase statistical power relative to the completely randomized design. It is argued that the advantages attributed to the block design are not always valid and that there are circumstances when the ANCOVA would be preferred to post-hoc blocking.…

Student self-selection in deciding to repeat a test was examined by contrasting the test performance of students taking the Scholastic Aptitude Test (SAT) as juniors and again as seniors with the test performance of students taking the SAT only once as juniors. Results suggest there is self-selection in test repetition. (Author/GK)

Statistics used to estimate the population correlation ratio were reviewed and evaluated. The sampling distributions of Kelly's and Hays' statistics were studied empirically by computer simulation within the context of a three level one-way fixed effects analysis of variance design. (Author/RC)

The subscales of the Bristol Social Adjustment Guides are compared with those of the Behavior Problem Checklist so as to test the hypothesis of a two-factor structure in these rating scales. The specificity of each subtest was also investigated. (Author/GK)

A number of empirical studies are suggested to answer certain questions in connection with flexilevel tests. (MS)

The purpose of this study was to determise the relative loss in statistical power of traditional methods of analysis when response-shift bias is present. Five methods of analysis (posttest scores only; postminus pretests; postminus retrospective pretest; postcovaried by pretest; postcovaried by retrospective pretest) were compared. (Author/BW)

Ignorance of the characteristics of a mixed population may lead to bias in a summary measure of a phenomenon. A test based on sample kurtosis is demonstrated by a simulation study to be more powerful than six other known tests in detecting a class of mixed normal distributions. (SLD)