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…

District costs for teachers' health insurance are, on average, higher then employer costs for private-sector professionals. How much of this is attributable to collective bargaining? This article examines the question using data from the National Compensation Survey (NCS) of the Bureau of Labor Statistics (BLS) and the state of Wisconsin. In…

We use visualization to find patterns in educational data. We represent student scores from high-stakes exams as flow vectors in fluids, define two types of streamlines and trajectories, and show that differences between streamlines and trajectories are due to regression to the mean. This issue is significant because it determines how quickly…

This study provided a preliminary analysis of concurrent and discriminative validity for the "Early Literacy Progress Monitoring Assessment Tool" (ELP-MAT; Kaderavek, 2009). Sixty preschool students between the ages of 3 years, 6 months and 5 years of age, from early childhood programs in Northwest Ohio, participated in the study. The…

Background: Telerehabilitation is the remote delivery of rehabilitation services via information technology and telecommunication systems. There have been a number of studies that have used videoconferencing to assess speech and language skills in people with acquired neurogenic communication disorders. However, few studies have focused on cases…

The potential of the Rasch model to develop scores, on a ratio scale, suitable for interindividual comparisons, from intact groups with disparate distribution characteristics was investigated. The specific problems studied were: (1) the effects of skewed test score distributions on the ability parameter of the Rasch measurement model; (2) the…

Observed percentiles provide better estimates when they are based on grouped data rather than on raw data. This is especially true when the data set is relatively small and the population distribution is not too skewed or heavy-tailed. Applied statisticians could take advantage of this fact by implementing a program for estimating percentiles from…

Two relatively new tools for analysis of data compiled in evaluation studies are presented. The National Test-Equating Study in Reading, known as the Anchor Test Study, produced tables of score-correspondence between the eight reading comprehension and vocabulary tests most widely used in the United States. Two types of tables from this report…

This report contains the selected descriptive analysis of the Anchor Test Study. Data originates in the public school segment of the national sample of grades 4, 5, and 6 who were administered the appropriate level of the Metropolitan Achievement Test (MAT): Reading, Form F. A description of the determination of the data base, of the analyses and…

The performance of three equating methods--the presmoothed equipercentile method, the item response theory (IRT) true score method, and the IRT observed score method--were examined based on three equating criteria: the same distributions property, the first-order equity property, and the second-order equity property. The magnitude of the…

This report is an integral part of the publication series of the Youth in Transition study, a nationwide panel survey of adolescent boys, which attempts to discover and document how the contemporary social environments affect the development of young men during their high school years. Four waves of data were gathered from 2,213 boys comprising…

Addresses the Welsh school-effect in which schools in Wales generally have lower school outcome measures compared to England although the growing number of Welsh medium schools in South Wales are doing better. Suggests an alternative way of analyzing school performance data that leads to the opposite conclusion on both propositions. (CMK)

Proposes that, while there may be real sex differences in vocational interests, Gottfredson's reanalysis of Self-Directed Search predictive data provides no support for the counseling use of sex-divergent raw interest scores. (RC)

The federally funded longitudinal field study called Management Implications of Team Teaching (MITT) required a search for an appropriate strategy for analyzing through-time relationships among selected variables. The MITT project used questionnaires and interviews to collect data concerning the work, governance, attitudes, and orientation of…

This report examines the difference in approaches between sociologists and psychologists when using multiple regression techniques in the analysis of behavioral data. Psychologists and sociologists are often divided in their orientation toward regression techniques, and this division could be a substantial and unfortunate barrier to communication…