The meta-analytic method proposed by S. W. Raudenbush (1988) for studying variance heterogeneity was studied. Results of a Monte Carlo study indicate that the Type I error rate of the test is sensitive to even modestly platykurtic score distributions and to the ratio of study sample size to the number of studies. (SLD)

A Monte Carlo evaluation of four test statistics for comparing dependent zero-order correlations was conducted with four sample sizes and three population distributions. Results indicate that choice of optimal test statistic depends on sample size and distribution, and predictor intercorrelation and effect size or magnitude of the…

A modification of the Mantel Haenszel (MH) procedure in which the sample is broken in half and subsamples are studied separately was compared with a residual procedure based on item response theory as a way to detect differential item functioning (DIF). Results suggest that the residual analysis achieves higher DIF detection. (SLD)

Several methods of constructing confidence intervals for Spearman's rho (rank correlation coefficient) (C. Spearman, 1904) were tested in a Monte Carlo study using 2,000 samples of 3 different sizes. Results support the continued use of Spearman's rho in behavioral research. (SLD)

Proposes a method for the comparative analysis of concentration in author productivity distributions; selects suitable measures, Gini's index and number of authors, for two viewpoints regarding productivity; discusses statistical peculiarities of author productivity data; and explains developmental profiles which take into account sample size…

Uses action research items to help students realize the importance of sample size in statistical analysis. (YDS)

A Monte Carlo study involving 1,000 random samples from each of 64 different population matrices investigated bias in both canonical correlation and redundancy coefficients. Results indicate that the Wherry correction provides a reasonable solution to this problem and that canonical results are not as biased as has been believed. (TJH)

A Monte Carlo study was conducted to examine the performance of several strategies for estimating the squared cross-validity coefficient of a sample regression equation in the context of best subset regression. Results concerning sample size effects and the validity of estimates are discussed. (TJH)

The nonnormed fit index's dependence on sample size in covariance structure analysis is discussed. Contrary to K. A. Bollen (1986) (whose alternative index depends on sample size), it is shown that the mean of the nonnormed fit index is independent of sample size for true and almost true models. (Author/TJH)

The performance was studied of five small-sample statistics--by F. M. Lord, W. Kristof, Q. McNemar, R. A. Forsyth and L. S. Feldt, and J. P. Braden--that test whether two variables measure the same trait except for measurement error. Effects of non-normality were investigated. The McNemar statistic was most powerful. (TJH)

Four commonly used tests for treatment-control group differences are compared. Use of analysis of covariance plus alternate rank assignments was found superior to other methods, especially in the small sample cases typical of research in the area of severe-profound retardation. (Author/DB)

The accuracy of four empirical techniques to estimate shrinkage in multiple regression was studied through Monte Carlo simulation. None of the techniques provided unbiased estimates of the population squared multiple correlation coefficient, but the normalized jackknife and bootstrap techniques demonstrated marginally acceptable performance with…

Large-sample standard errors of linear equating for the counterbalanced design are derived using the general delta method. Computer simulations found that standard errors derived without the normality assumption were more accurate than those derived with the normality assumption in a large sample with moderately skewed score distributions. (SLD)

A QuickBASIC microcomputer program for conducting Tukey-like pairwise comparisons on "k" independent sample proportions is described. The program can accommodate applications involving equal or unequal sample sizes. Studentized range values are computed and displayed on a computer monitor, each of which represents a simple comparison…

Suggest practical procedure for estimating number of subjects that need to be screened to obtain sample of fixed size that meets multiple correlated criteria. Procedure described is based on fact that least-squares regression provides good quadratic fit for Monte Carlo estimates of multivariate probabilities when they are plotted as function of…