Discusses a 1976 survey of Comprehensive Employment and Training Act participants and factors affecting the success or failure of employment programs. (JOW)

Queuing networks, mixed integer programing, and expected utility theory are combined together to model the library building programing problem. Thirty-nine references are cited. (Author/FM)

Inference procedures appropriate for the analysis of nominal and ordinal data are discussed. Matching models are shown to be useful under certain constraints. (JKS)

Argues that citizens' perceptions of their monetary self-interest can markedly influence their votes and that such self-interested voting requires clear definition of the alternatives, widespread publicity about the issues, and a simple presentation of what each alternative implies. Available from NTA-TIA, 21 East State Street, Columbus, OH 43215.…

The direct estimates of the relationship between permanent income and property tax payments presented here suggest that the property tax on homeowners is progressive at the national level and generally proportional at the local level. Available from NTA-TIA, 21 East State Street, Columbus, OH 43215. (Author)

Challenge studies can be used to see whether there is a causal relationship between an agent of interest and a response. An approach based on union-intersection testing is presented that allows researchers to examine observations on a single subject and test the hypothesis of interest. An application using psychological data is presented. (SLD)

An integration of two different approaches to the psychology of causal induction is proposed that overcomes the problems associated with each. The proposal results in a causal power theory of the probabilistic contrast model of P. W. Cheng and L. R. Novick (1990). (SLD)

Investigated whether the "ontological reversal" described by E. Husserl, the tendency to view abstract mathematical models of phenomena as more real than the phenomena themselves, is present in the reasoning of pre-service science teachers. Findings for 23 pre-service teachers indicate the presence of the ontological reversal as a figure…

Develops a model of mathematical learning from an exploration of educational research and personal observations. Uses Kolb's model of experiential learning to characterize four mathematical learning styles: (1) allegorizers; (2) integrators; (3) analyzers; and (4) synthesizers. These styles are viewed as corresponding to four stages of…

Presents an overview of Rasch measurement models that begins with a conceptualization of continuous experiences often captured as discrete observations. Discusses the mathematical properties of the Rasch family of models that allow the transformation of discrete deterministic counts into continuous probabilistic abstractions. Also discusses six of…

A method based on homogeneity analysis (multiple correspondence analysis or multiple scaling) is proposed to reduce many categorical variables to one variable with "k" categories. The method is a generalization of the sum of squared distances cluster analysis problem to the case of mixed measurement level variables. (SLD)

This note shows that the formula suggested by N. D. Bryant and S. Gokhale (1972) for correcting indirectly restricted correlations when no information is available on the third (directly restricted) variable is accurate only in one special instance. A more general correction formula is illustrated. (SLD)

Means of identifying sources of rejection of hypotheses regarding linear multivariate statistical models are discussed. Problems with the use of a global test using Roy's largest root criterion and means of solving them are presented, along with a practical application of the techniques. (TJH)

A model which approaches the problem of characterizing distributions of test validity correlation coefficients from the perspective of finite mixture theory is presented. This estimation method offers advantages over validity generalization procedures. Examples are provided to illustrate applications of the method. (SLD)

The structure of information matrices in latent-variable models is explicated, and the degree to which missing information can be recovered by exploring collateral variables for respondents is characterized. Results are illustrated in the context of item-response-theory models, and practical implications are discussed. (SLD)