The use of p-values in combining results of studies often involves studies that are potentially aberrant. This paper proposes a combined test that permits trimming some of the extreme p-values. The trimmed statistic is based on an inverse cumulative normal transformation of the ordered p-values. (SLD)

Estimation/smoothing methods that are flexible enough to fit a wide variety of test score distributions are reviewed: kernel method, strong true-score model-based method, and method that uses polynomial log-linear models. Applications of these methods include describing/comparing test score distributions, estimating norms, and estimating…

A method is presented that eliminates some interpretational limitations arising from assumptions implicit in the use of arbitrary rules of thumb to interpret exploratory factor analytic results. The bootstrap method is presented as a way of approximating sampling distributions of estimated factor loadings. Simulated datasets illustrate the…

Asymptotic distributions of H. Brogden's and F. Lord's modified sample biserial correlation coefficients (SBCCs) are derived. Asymptotic variances of these estimators are evaluated for bivariate normal populations and compared to the maximum likelihood estimator's asymptotic variance. These estimators are less variable than ordinary SBCCs when the…

The derivation of the variance of similarity judgments is made from the 3-D process in nonlinear psychophysics. The idea of separability of dimensions in metric space theories of similarity is replaced by one parameter that represents the degree of a form of interdimensional cross-sampling. (SLD)

Performance of the logistic regression (LR) procedure was compared to that of the Mantel Haenszel (MH) procedure in the detection of uniform and nonuniform differential item functioning on a simulation examining distributional properties of the LR and MH test statistics and the relative power of the two procedures. (SLD)

Alternative models for a large dataset were analyzed by asymptotically distribution-free, generalized least squares, maximum likelihood, and ordinary least squares estimation methods, comparing incremental and nonincremental fit indexes. Incremental methods were quite unstable across estimation methods. This phenomenon is explained. (SLD)

Derives a set of linear conditions of item-response functions that guarantees identical observed-score distributions on two test forms. The conditions can be added as constraints to a linear programming model for test assembly. An example illustrates the use of the model for an item pool from the Law School Admissions Test (LSAT). (SLD)

A Monte Carlo study was conducted using simulated dichotomous data to determine the effects of guessing on Rasch item fit statistics and the Logit Residual Index. Results indicate that no significant differences were found between the mean Rasch item fit statistics for each distribution type as the probability of guessing the correct answer…

Presents abstracts of papers for a planned session dealing with the historiography and history of information science. Highlights include probability distributions underlying the use of library materials, particularly scientific journals; the temporal and historical orientation of the rhetoric of information science; and concepts of information…

An objective method is presented to group discrete self-injurious behavior (SIB) events into bouts. Survival analysis was used to determine how long after an SIB the probability of observing a subsequent SIB remained elevated. This estimated bout length criterion time point was determined individually for 19 subjects with developmental disorders…

In contrast with statements by institutions and science organizations about why science should be studied, nonscience majors at two-and four-year institutions said they were enrolled in a science course because it was required rather than because it would help them get the job they desired or would enrich them personally. (Contains 2 tables and 5…

A new item parameter replication method is proposed for assessing the statistical significance of the noncompensatory differential item functioning (NCDIF) index associated with the differential functioning of items and tests framework. In this new method, a cutoff score for each item is determined by obtaining a (1-alpha ) percentile rank score…

Purpose: This article sheds light on some basic questions about the distribution of educational leadership preparation degree programs among different types of institutions and the distribution of advanced degrees, by type, exploring change over time and the relationship to regional labor market estimates. Method: We used data from five major…

The main goal of this study was to assess how sensitive unidimensional parameter estimates derived from BILOG were when the unidimensionality assumption was violated and the underlying ability distribution was not multivariate normal. A multidimensional three-parameter logistic distribution that was a straightforward generalization of the…