General guidelines are developed to assist practitioners in devising operational computerized adaptive testing systems based on the graded response model. The effects of the following major variables were examined: item pool size; stepsize used along the trait continuum until maximum likelihood estimation could be calculated; and stopping rule…

Demonstrates that magnitude-of-effects (ME) estimates vary in susceptibility to sample-size bias depending on whether they are directional or nondirectional estimates. Also demonstrates that study characteristics that influence size of ME estimates can be explicitly taken into account when comparing studies. Emphasizes need to consider study…

It is suggested that using an unbiased estimate of the weight matrix may eliminate the small or intermediate sample size bias of the asymptotically distribution-free (ADF) test statistic. Results of simulations show that test statistics based on the biased estimator or the unbiased estimate are highly similar. (SLD)

In multivariate analysis of variance studies with small numbers of subjects (15 or less) per treatment level, probability values reported by the commercial statistical packages SAS and SPSS are conservative for F approximations based on Pillai's trace and liberal for F approximations based on the Hotelling-Lawley trace. Discusses results in terms…

Focusing on linear interpolation, an accurate method of implementing parallel analysis, this article contains tables of 95th percentile eigenvalues from random data than can be used with sample sizes of 50 to 500 subjects and between 5 and 50 variables. An empirical example illustrates how to obtain the eigenvalues. (SLD)

Provides an introduction to sampling, determination of sample size, and selection of the actual sample that would be useful for librarians conducting research and evaluation studies. Highlights include sampling method, sampling error, confidence level, and microcomputer software packages that help determine sample size. (Contains 26 references.)…

Previous work on the effects of dimensionality on parameter estimation for dichotomous models is extended to the graded response model. Datasets are generated that differ in the number of latent factors as well as their interdimensional association, number of test items, and sample size. (SLD)

A sample of chronic postconcussive patients with and without overt malingering signs was compared with objectively brain-injured patients (total sample=106) on common episodic memory and malingered amnesia measures. Findings validate commonly cited malingering measures and new methods of classifying malingering in real-world clinical samples. (SLD)

Analytical solutions for point and variance estimators of the mediated effect, the ratio of mediated to direct effect, and the proportion of the total effect mediated were determined through simulation for different samples. The sample sizes needed for accuracy and stability are discussed with implications for mediated effects estimates. (SLD)

Five methods for testing the hypothesis of independence between two sets of variates were compared through simulation. Results indicate that two new methods, based on robust measures reflecting the linear association between two random variables, provide reasonably accurate control over Type I errors. Drawbacks to rank-based methods are discussed.…

The one-sided problem of comparing treatments with a standard on the basis of data available in the context of a one-way analysis of variance is examined, and the methodology of S. Chakraborti and J. D. Gibbons (1991) is extended to the case of unequal sample sizes. (SLD)

E.J. Bedrick recently derived the asymptotic distribution of the modified sample biserial correlation estimator of F.M. Lord and studied its efficacy for bivariate normal populations. A more detailed examination of the properties of Lord's estimator is provided, and the small sample bias and variance are studied. (SLD)

The routine epsilon approximate test in repeated measures designs when the condition of circularity is unfulfilled uses an erroneous formula in the case of two or more groups. Because this may lead to underestimation of the deviation from circularity when the subject number is small, a correction is proposed. (Author/SLD)

Using a Monte Carlo simulation, a bootstrap procedure was evaluated for setting a confidence interval on the unrestricted population correlation (rho) assuming various degrees of incomplete truncation on the predictor. Sample size was the most important factor in determining accuracy and stability. Sample size should be at least 50. (SLD)

This Monte Carlo simulation studied the relative power of 8 tests for sphericity in randomized block designs where sample size was small (10, 15, 20, and 30) and population covariance matrices of dimension-to-sample size ratio approached 1.0. The locally best invariant test demonstrated substantial power to detect departures from sphericity. (SLD)