New knowledge tracing models are continuously being proposed, even at a pace where state-of-the-art models cannot be compared with each other at the time of publication. This leads to a situation where ranking models is hard, and the underlying reasons of the models' performance -- be it architectural choices, hyperparameter tuning, performance…

Proactive preliminary minimum sample size determination can be useful for the early planning stages of a latent variable modeling study to set a realistic scope, long before the model and population are finalized. This study examined existing methods and proposed a new method for proactive preliminary minimum sample size determination.

The goal of this study was to examine the extent to which preschoolers with externalizing behavior problems (EBP) can identify behaviors indicative of callous-unemotional (CU) traits among their peers. Participants for this study included 86 preschool children (69% boys; M[subscript age] = 5.07 years) with at-risk or clinically elevated levels of…

Federal initiatives and other research have led states across the nation to sharpen their focus on teacher evaluation in recent years. In 2009 a seminal report, "The Widget Effect," from The New Teacher Project revealed that in districts using a binary rating system to evaluate teachers, less than 1 percent of teachers received an…

The Research Alliance for New York City Schools examined Department of Education (DOE) School Survey data from 2008-2010 to better understand the richness and complexities of the information elicited by the Survey from parents, students, and teachers. This document provides the appendices to the technical report "New York City School Survey…

In recent times social capital has received considerable attention because it is seen as having the potential to address many of the problems facing modern society, including the poor educational outcomes of considerable numbers of young people. This paper uses data from the Longitudinal Surveys of Australian Youth (LSAY) to explore the…

Real world data often fail to meet the underlying assumption of population normality. The Rank Transformation (RT) procedure has been recommended as an alternative to the parametric factorial analysis of Covariance (ANCOVA). The purpose of this study was to compare the Type I error and power properties of the RT ANCOVA to the parametric procedures…

The multiplicity of variables describing the financial conditions of postsecondary institutions makes it difficult to assess changes in higher education finance from year to year and to find the relationship between these finance variables and average faculty salaries. This study sought to determine if a small number of factors could be derived to…

The results of this study conclude that there is a multidimensional basis for test score inferences on the mathematics and critical reading sections of the SAT. Results from the exploratory analyses indicate that the data are multidimensional, as mathematics displayed two dimensions and critical reading displayed three dimensions. The correlations…