Presents a model of college entrance that focuses on the influences of public policy and the economic environment, and the interaction of these factors with student ability and parental income. (TA)

In the context of pass/fail decisions, using the Bock multi-nominal latent trait model for moderate-length tests does not produce decisions that differ substantially from those based on the raw scores. The Bock decisions appear to relate less strongly to outside criteria than those based on the raw scores. (Author/JAZ)

Giving patterns in the six years following a stock market drop in 1960 showed that giving actually went up during those years. However, in the case of very wealthy donors, they reduced large gifts to colleges. ( MLW)

Two experiments employed story telling to investigate whether production is adapted to comprehension. Subjects were more likely to specify instruments from stories if the instruments were atypical or important to the story. A mathematical model proposed that instrument concepts may be selected at three stages in the production process. (Author/LMO)

In this paper a Bayesian procedure is developed for the simultaneous estimation of the reading ability and difficulty parameters which are assumed to be factors in reading errors by the multiplicative Poisson Model. According to several criteria, the Bayesian estimates are better than comparable maximum likelihood estimates. (Author/JAZ)

Two easily computed test statistics are proposed for testing the equality of two correlated proportions when some observations are missing on both responses. The performance of these tests in terms of size and power is compared with other tests by means of Monte Carlo simulations. (Author/BS)

A meta analysis of preschool intervention programs is performed to arrive at an overall effect size of such programs. Results indicate that despite the diversities in intervention sites, ages of subjects, lengths of intervention, and curricula models, there is a positive homogeneous effect on the variables. (Author/LMO)

Standard maximum likeliheed estimation was compared using two forms of robust estimation, BIWEIGHT (based on Tukey's Biweight) and AMTJACK (AMT-Robustified Jackknife), and Rasch model person analysis. The two procedures recovered the generating parameters, but Rasch person analysis also helped to identify the nature of a response disturbance. (GDC)

Advantages and disadvantages of joint maximum likelihood, marginal maximum likelihood, and Bayesian methods of parameter estimation in item response theory are discussed and compared. (Author)

The many methodological contributions of Raymond B. Cattell to multivariate analysis are discussed in terms of contemporary issues in structural equation modeling. His factor analytic approach is compared with current modeling practices. A critical evaluation finds much of Cattell's work still innovative, technically advanced, and valuable to…

Using the analogy of temperature measurement, the Rasch model is presented with arguments for its adoption as the basic scaling technique for achievement measures. Three extensions of the Rasch model for more complex testing are developed. Test development for the British national assessment program and the promise of item banking are also…

Proposes approach to integrating Boolean and statistical systems where Boolean queries are interpreted as a means of specifying term dependencies in relevant set of documents. Highlights include series of retrieval experiments designed to test retrieval strategy based on term dependence model and relation of results to other work. (18 references)…

This study examined the influence of processing strategies, and the metacomponents that determine when to apply them, on the construct validity of a verbal reasoning test. A rule-oriented strategy, an association strategy, and a partial rule strategy were examined. All three strategies contributed to individual differences in verbal reasoning.…

An approach to teaching the exponential function using discrete methods, rather than continuous analysis, is presented. A model for simple geometric growth is explored, with a computer program given. (MNS)

A newly introduced approach, rule space, can represent large numbers of erroneous rules of arithmetic operations quantitatively and can predict the likelihood of each erroneous rule. The new model challenges the credibility of the traditional right-or-wrong scoring procedure. (Author/PN)