When investigating differences between two sets of scores, the t test is appropriate. If the two sets of data are from two groups of subjects, then the independent t test is appropriate. If the two sets are from the same subjects, the dependent t test is required. In this paper, the authors describe the use of a third test when part of a data set…

The Cochran Q and the Minimum X sub one squared statistics are two ways to test a hypothesis of equivalent correlated proportions. This study investigated the small sample properties of Q and X sub one squared by Monte Carlo methods. The observed distributions were compared for their rates of covergence to the limiting theoretical X sub one…

There are good reasons for the growing popularity of Monte Carlo procedures; but with increasing use comes increasing misuse. A variety of exact and approximate alternatives should be considered before one chooses to approach a problem with Monte Carlo methods. Once it has been decided that simulation is desirable, consideration should be given to…

Simultaneous test procedures (STPS for short) in the context of the unrestricted full rank general linear multivariate model for population cell means are introduced and utilized to analyze interactions in factorial designs. By appropriate choice of an implying hypothesis, it is shown how to test overall main effects, interactions, simple main,…

A computer-simulated study was made of the sampling distribution of omega squared, a measure of strength of relationship in multivariate analysis of variance which had earlier been proposed by the author. It was found that this measure was highly positively biased when the number of variables is large and the sample size is small. A correction…

The purpose of the Neyman-Johnson statistical technique is to determine a region or span of values on r independent variables where the predicted criterion scores of two or more treatment groups are significantly different. Consequently, the technique should prove especially useful in research concerned with moderator variables or with the…

A numerical procedure is outlined for obtaining an interval estimate of true score. The procedure is applied to several sets of test data. (Author)

The primary purpose of the present study was to investigate the appropriateness of several tests of significance for use with interrupted time series data. The second purpose was to determine what effect the violation of the assumption of uncorrelated error would have on the three tests of significance. The three tests were the Mood test,…

A specific form of nonrandom assignment to treatment groups, the "alternate ranks" design, was investigated. This design eliminates the possibility of a correlation between the covariate and the treatment, and rules out experimenter bias in assignment of subjects to groups. (Editor)

The effects of the violation of the assumption of homogeneity of regression on the Type I error rate and on the power of analysis of covariance are investigated. The results indicate that analysis of covariance is robust when sample sizes are equal. (Author/JKS)

The partitioned-U procedure is outlined, a fundamental logical flaw in this procedure's avoidance of any direct test of the significance of the first discriminant function or largest coefficient of canonical correlation is pointed out, and two alternatives to the partitioned-U procedure are discussed. (Author/DEP)

Two stage multiple-comparison procedures give an exact solution to problems of power and Type I errors, but require equal sample sizes in the first stage. This paper suggests a method of evaluating the experimentwise Type I error probability when the first stage has unequal sample sizes. (Author/BW)

Discusses difficulties encountered in use of the Scheffe procedure to locate the most significant parametric function within a linear statistical model that has been tested and rejected by, for example, analysis of variance. A solution to the problems is presented. (TJH)

The dangers of equating "statistical significance" with "real world" significance are summarized. When a finding is said to have "statistical significance," it means only that the same results would be likely to occur again if the study were repeated, not that the finding has any true personal or societal importance. (VW)

Designed to measure end-users' efficacy in online searching based on their presearch experience with printed literature retrieval systems for the search topic, this experiment examined differences between manual searches preceding electronic searches and vice versa. The results were not statistically significant due to the small sample size.…