POLYFACT is a learning program that attempts to factor multivariable polynomials. The program has been successful in factoring polynomials (in simplified form) with a maximum of 84 terms, each term consisting of as many as five variables and a maximum degree of 67. The complexity of this learning task placed unusual requirements on the…

A new heuristic factorization scheme uses learning to improve the efficiency of determining the symbolic factorization of multivariable polynomials with interger coefficients and an arbitrary number of variables and terms. The factorization scheme makes extensive use of artificial intelligence techniques (e.g., model-building, learning, and…

This paper explains how a major statistical package (BMDP) can be used to produce partial, semipartial, or bipartial set correlation in terms of a procedure outlined by Karpman (1980). (BW)

The purposes of the paper were to develop a structure by which assessment models could be uniquely characterized and to develop assessment models and their associated computer programs which could be used for personnel research purposes. To these ends two aspects of assessment, measurement and evaluation, were identified. Their distinction was…

The Design of Training Systems (DOTS) model was conceived to provide Naval Education and Training Command management with computerized mathematical models to assist in predicting the quantitative impact of training resource decisions. During Phase III of the project, the three models were operationally tested, and an evaluation team concluded that…

A query language which is suitable for use with a relational data base system is discussed. The language is developed as an extension of ideas found in programming languages as well as relational calculus. The development is a step towards the integration of programming languages, query languages, and data base systems. The language offers a…

In a LISREL-IV analysis, a method of specifying a priori the variances of the latent variables for interpretability is demonstrated. The potential confusion of the metric of the latent variables is discussed, since many of the parameter estimates are a function of the metric. (Author/CM)

The Educational Simulation Model (ESM), developed by UNESCO, is designed for use at the national level for long range simulation of educational system fluctuations. The model is a set of equations which describe an educational program and the changes and flows in student enrollment in all the courses of an educational system. Thus the model is…

A research project developed a computer program for analyzing time series quasi-experimental data. The program generates a nonstationary, integrated moving average time series model; it is used to estimate a parameter which indexes the instantaneous change in level of the time series due to a predesignated treatment. The entire method is based on…

The results of data analysis based on the multiplicative binomial model (MLTBIN) are compared with dichotomous data analyzed by using the simple logistic model (SLM). Specifically, the paper focuses on the issues of fit to these Rasch Models and estimates of item difficulty. The data indicate that the SLM and MLTBIN are not comparable in the…

An alternative item-selection procedure for use with Owen's Bayesian adaptive testing strategy is proposed. This procedure is, by design, faster than Owen's original procedure because it searches only part of the total item pool. Item selections are, however, identical for both methods. After a conceptual development of the rapid-search procedure,…

Although analysis of variance is the most popular statistical tool to researchers in the behavioral sciences, the casual user has recognized only recently that there is no single correct way to perform such an analysis. This paper is concerned with hypotheses tested in the two-way, fixed model under a variety of conditions: (1) with and without…

Current computer programs for analyzing linear structural models will apparently handle only two types of constraints: fixed parameter and equal parameters. In this paper, a method for imposing several types of inequality of parameter constraints is described. Several examples are presented. (Author/JKS)

Various models have been proposed for analyzing dichotomous test or questionnaire items which were constructed to reflect an assumed underlying structure (e.g., hierarchical). This paper shows that many such models are special cases of latent class analysis and discusses a currently available computer program to analyze them. (Author/JKS)

A family of models for the representation and assessment of individual differences for multivariate data called PINDIS (Procrustean Individual Differences Scaling) is presented. PINDIS sheds new light on the interpretability and applicability of a variety of multidimensional scaling models. (Author/JKS)