Categorical data become increasingly ubiquitous in the modern big data era. In this dissertation, we propose novel statistical learning and inference methods for large-scale categorical data, focusing on latent variable models and their applications to psychometrics. In psychometric assessments, the subjects' underlying aptitude often cannot be…

This article addresses the problem of estimating the proportion Pi[subscript S] of the population belonging to a sensitive group using optional randomized response technique in stratified sampling based on Mangat model that has proportional and Neyman allocation and larger gain in efficiency. Numerically, it is found that the suggested model is…

We discuss a recent development in the set theoretic analysis of data sets characterized by limited diversity. Ragin, in developing his Qualitative Comparative Analysis (QCA), developed a standard analysis that produces parsimonious, intermediate, and complex Boolean solutions of truth tables. Schneider and Wagemann argue this standard analysis…

This study of early childhood and the family in member countries of the Organisation for Economic Co-Operation and Development (OECD) employs two statistical approaches to the problem of providing an accurate picture of modern conditions of family life. A classical demographic approach to population studies is initially used, then is critiqued,…

Presents first of two-part editorial (second part to appear in next journal issue) proposing guidelines for developing useful tables to report multiple regression outcomes. Pays particular attention to situations where a hierarchical multiple regression analysis is guided by theory. Concludes that some conventional way to report multiple…

Some contemporary trends in social and clinical psychology suggest that individual differences in imaging abilities may become increasingly important. Outlines some of the conceptual and methodological problems that must be clarified if productive research is to be undertaken and reports results of three studies designed to isolate tests which…

Simulations show effects of variability on the maximum contingency that can be displayed by an average 2 X 2 table. Results help explain the regularity known as the Tulving-Wiseman law, as well as conditions under which exceptions are found. Dangers posed by variability and Simpson's paradox are discussed. (SLD)

Looks at the differences in quality in competency studies and cautions that trainers should be sure that the competencies identified are, in fact, valid and useful. Offers guidelines for identifying and describing competencies that are important to employees in a specific organization. (JOW)

Presents national data on teacher salary trends from 1967 to 1980 as background for a review of 15 major studies on collective bargaining's effects on teacher salaries. Discusses problems in the research and concludes that the studies indicate bargaining has had some effect on salaries. (RW)

Educational distribution tables were constructed which indicate that, generally, schools and school districts that scored in the upper (or middle, or lower) third of a ranking of Michigan districts on composite achievement also ran high (or middle, or low) on other assessment measures. The same type of relationship was generally found between…

In this paper, tables for the appropriate sample sizes are presented and discussed in the context that the determination of the effect size must precede the determination of the sample size. (Author/PN)

Provides a critique of research done by A. M. Dockery, R. Kelly, K. Norris, and T. Strombeck regarding the cost and value of hiring trainees. Discusses the perceived shortcomings in the method and looks at the implications of the research. Dockery et al. provide a rejoinder. (JOW)

In educational effectiveness research, multilevel models are increasingly used because these models take the multilevel structure of the data into account. In this paper, the effect of ignoring one or more levels of variation in hierarchical linear regression is explored, using a model with four hierarchical levels (individual pupil, class group,…

As an extension of B. Thompson's 1998 invited address to the American Educational Research Association, this paper cites two additional common faux pas in research methodology and explores some research issues for the future. These two errors in methodology are the use of univariate analyses in the presence of multiple outcome variables (with the…