The need for scale linking in the National Assessment of Educational Progress (NAEP) is discussed, and the specific procedures used to carry out the linking in the context of the major analyses of the 1990 NAEP mathematics assessment are described. Issues remaining to be addressed are outlined. (SLD)

Results of empirical validation studies of six statistical models available for indirectly estimating the need for alcohol, drug abuse, and mental health services across a large geographic area are presented. Models were evaluated using Colorado Social Health Survey data for 4,745 adults from 48 subareas of Colorado. (SLD)

A nonparametric multicategorical model for multiple-choice data is proposed as an extension of the binary spline model of J. O. Ramsay and M. Abrahamowicz (1989). Results of two Monte Carlo studies illustrate the model, which approximates probability functions by rational splines. (SLD)

A method for analyzing test-item responses is proposed to examine differential item functioning (DIF) in multiple-choice items within the latent class framework. Different models for detection of DIF are formulated, defining the subgroup as a latent variable. An efficient estimation method is described and illustrated. (SLD)

Calculating the reliability of a testlet-based test is demonstrated using data from 1,812 males and 2,216 females taking the Scholastic Aptitude Test verbal section and 3,866 examinees taking another reading test. Traditional reliabilities calculated on reading comprehension tests constructed of four testlets provided substantial overestimates.…

A conceptual approach and a set of computer simulations are presented to demonstrate that random measurement error in the pretest does not bias the estimate of the treatment effect in the regression-discontinuity design. Focus is on the case of no interaction between pretest and treatment on posttest. (SLD)

Traditional measures indicating little net change in long-term poverty for children between the late 1960s and the early 1980s mask certain statistical and demographic changes. A rise in female-based households, fewer well-paying jobs for younger workers, and greater dependence on social assistance have offset smaller family sizes and parental…

A synthetic method of estimating relative annual prevalence of severely mentally disabled (SMD) adults across Ohio's mental health board areas was evaluated. Indirect evidence of accuracy for the method, which relies on local catchment area data and local census data, is provided by comparison with actual SMD adult counts in federal programs. (SLD)

Selected examples using the statistical packages Statistical Package for the Social Sciences (SPSS), the Statistical Analysis System (SAS), and BMDP are presented to facilitate their use and encourage appropriate uses in: (1) a hierarchical design; (2) a confounded factorial design; and (3) variance component estimation procedures. To illustrate…

The adequacy of several approaches to estimation of proficiency distributions for the Trial State Assessment (TSA) in eighth grade mathematics of the National Assessment of Educational Progress was examined. These approaches are more restrictive than the estimation procedures originally used, with the same kind of plausible-values approach that…

Methods for predicting specific college course grades, based on small numbers of observations, were investigated. These methods use collateral information across potentially diverse institutions to obtain refined within-group parameter estimates. One method, referred to as pooled least squares with adjusted intercepts, assumes that slopes and…

The shortcomings of the conventional way of using and interpreting multiple-choice tests are summarized. Some theories and methodologies that can be applied for better use multiple-choice test items are described. Empirical facts are introduced to support the theoretical observations. New strategies are proposed that will reduce "noise"…

This paper presents an introduction to the use of latent trait models for the estimation of domain scores. It was shown that these models provided an advantage over classical test theory and binomial error models in that unbiased estimates of true domain scores could be obtained even when items were not randomly selected from a universe of items.…

Multidimensional item difficulty (MID) is proposed as a means of describing test items which measure more than one ability. With mathematical story problems, for instance, both mathematical and verbal skills are required to obtain a correct answer. The proposed measure of MID is based upon three general assumptions: (1) the probability of…

Although policy makers have expressed interest in expenditures by private elementary and secondary schools, nationally representative data in this area are not available. In the absence of expenditure data it may nevertheless be possible to derive national estimates of total expenditures by private schools indirectly, by using the information that…