An approximation to the likelihood for the generalized linear models with random coefficients is derived and is the basis for an approximate Fisher scoring algorithm. The method is illustrated on the logistic regression model for one-way classification, but it has an extension to the class of generalized linear models and to more complex data…

The Monte Carlo study compared the performance of predictive discriminant analysis (PDA) and that of logistic regression (LR) for the two-group classification problem. Prior probabilities were used for classification, but the cost of misclassification was assumed to be equal. The study used a fully crossed three-factor experimental design (with…

The Johnson-Neyman (J-N) technique (P. Johnson and N. Neyman, 1936) is used to determine areas of significant difference in a criterion variable between two or more groups in situations of linear regression. In using this technique, researchers have encountered difficulties with results, possibly related to the J-N technique's sensitivity to…

How youngsters classified as educable mentally retarded performed academic math tasks in several types of token economies. (Author)

How youngsters classified as educable mentally retarded performed academic math tasks in several types of token economies. (Author)

A discussion of the simulated oral proficiency interview (SOPI), a type of semi-direct speaking test that models the format of the oral proficiency interview (OPI), describes its development and research and examines its usefulness. The test used for discussion is a tape-recorded test consisting of six parts, scored by a trained rater using the…

A recent survey of simulation studies concluded that an overwhelming majority of papers do not report a rationale for the number of iterations carried out in Monte Carlo robustness (MCR) experiments. The survey suggested that researchers might benefit from adopting a hypothesis testing strategy in the planning and reporting of simulation studies.…

In analyzing exploratory repeated measures data with more than two measures, two competing tests must be administered simultaneously if one is to make an efficient and effective decision regarding the tenability of the null hypothesis of no differences among measurement means. Obviously, such a procedure is not without a cost vis-a-vis Type I…

A fly-only group (N=16) of Navy replacement pilots undergoing fleet readiness training in the SH-3 helicopter was compared with groups pre-trained on Device 2F64C with: (1) visual only (N=13); (2) no visual/no motion (N=14); and (3) one visual plus motion group (N=19). Groups were compared for their SH-3 helicopter performance in the transition…

Two reduced rank classification procedures, principal components classification and equal weights classification, are described and compared by a simulation study to the standard classification procedure to determine their feasibilities as alternative classification procedures. A justification for the development of these two reduced rank…

This paper describes a computer model that simulates experimental outcome data obtained by the manipulation of 13 independent variables reported in studies investigating the group risky shift. The model is intended as a tool for teaching research methods in an undergraduate course in social psychology. (Author)