The fit of an item response model is typically conceptualized as whether a given model could have generated the data. We advocate for an alternative view of fit, "predictive fit", based on the model's ability to predict new data. We derive two predictive fit metrics for item response models that assess how well an estimated item response…

This commentary to the recent article by Musso et al. (2013) discusses issues related to model fitting, comparison of classification accuracy of generative and discriminative models, and two (or more) cultures of data modeling. We start by questioning the extremely high classification accuracy with an empirical data from a complex domain. There is…

Classification procedures are common and useful in behavioral, educational, social, and managerial research. Supervised classification techniques such as discriminant function analysis assume training data are perfectly classified when estimating parameters or classifying. In contrast, unsupervised classification techniques such as finite mixture…

Rough set theory (RST) is an emerging technique used to deal with problems in data mining and knowledge acquisition. However, the RST approach has not been widely explored in the field of academic achievement. This investigation developed an improved RST (IMRST) model, which employs linear discriminant analysis to determine a reduct of RST, and…

In this article we extend and implement the forward search algorithm for identifying atypical subjects/observations in factor analysis models. The forward search has been mainly developed for detecting aberrant observations in regression models (Atkinson, 1994) and in multivariate methods such as cluster and discriminant analysis (Atkinson, Riani,…

A large sample of 33,000 university alumni records were cluster-analyzed to generate six groups relatively unique in their respective attribute values. The attributes used to cluster the former students included average gift to the university's foundation and to the alumni association for the same institution. Cluster detection is useful in this…

Results of data analysis on 470 journal titles illustrate complexity of the fuzzy set theory modeling process, which consists of three factors--number of missing issues, citations, circulations--and its limitations in making journal binding decisions. Procedures of research, data collection, and data analysis are discussed. Matrices are included.…

Default on guaranteed student loans has been increasing. The use of discriminant analysis as a technique to identify "good" v "bad" student loans based on information available from the loan application is discussed. Research to test the ability of models to such predictions is reported. (Author/MLW)