Sociologists increasingly face choices among competing algorithms that represent reasonable approaches to the same task, with little guidance in choosing among them. We develop a strategy that uses simulated data to identify the conditions under which different methods perform well and applies what is learned from the simulations to predict which…

Background: For peer assessment, reliability (i.e., consistency in ratings across peers) and validity (i.e., consistency of peer ratings with instructors or experts) are frequently examined in the research literature to address a central concern of instructors and students. Although the average levels are generally promising, both reliability and…

Past research on knowledge has differentiated between dimensions of knowledge, for example amount or coherence. This dissertation introduces a novel dimension of knowledge, the Motivational Utility of Knowledge (MUK), that is based on hierarchies of human needs (e.g., physical safety, status/esteem, actualization, reproduction). The effects of MUK…

The multifaceted disruption of social and political processes during the most intense phases of the COVID crisis encouraged many groups and individuals to propose change and reform to education. This current report is a distinctive voice in the debate about 'assessment futures'. Not least, it outlines the nature of human construction of the…

Online Judge (OJ) systems are typically considered within programming-related courses as they yield fast and objective assessments of the code developed by the students. Such an evaluation generally provides a single decision based on a rubric, most commonly whether the submission successfully accomplished the assignment. Nevertheless, since in an…

This dissertation examines the effectiveness of machine learning algorithms and feature engineering techniques for analyzing process data and predicting test performance. The study compares three classification approaches and identifies item-specific process features that are highly predictive of student performance. The findings suggest that…

Most existing solutions to the current replication crisis in science address only the factors stemming from specific poor research practices. We introduce a novel mechanism that leverages the experts' predictive abilities to analyze the root causes of replication failures. It is backed by the principle that the most accurate predictor is the most…

We propose new ways of robustifying goodness-of-fit tests for structural equation modeling under non-normality. These test statistics have limit distributions characterized by eigenvalues whose estimates are highly unstable and biased in known directions. To take this into account, we design model-based trend predictions to approximate the…

Education is inherently entangled with the future. This argumentative review examines this entanglement and proposes a framework differentiating between four educational orientations towards the future. The orientation 'Futures of education' examines how education changes in the future: From rhetorical to visionary, these futures are concerned…

In recent years, knowledge tracing (KT) within intelligent tutoring systems (ITSs) has seen rapid development. KT aims to assess a student's knowledge state based on past performance and predict the correctness of the next question. Traditional KT often treats questions with different difficulty levels of the same concept as identical…

Recently, our course team transformed a large-enrollment introductory genetics course from being predominantly lecture based to active learning based. During class sessions, students engaged in problem solving, which occurs when a student attempts to solve a problem without knowing the path to complete it. We designed class activities…

In this paper, we explore the critical practice of making sense of students' mathematical ideas. We extend previous research by studying stances prospective teachers adopt, the extent or depth to which they do so, and the types of prospective teachers making sense of students' mathematical ideas. Analyzing the responses of 123 prospective teachers…

Deep learning models for text classification have been increasingly used in intelligent tutoring systems and educational writing assistants. However, the scarcity of data in many educational settings, as well as certain imbalances in counts among the annotated labels of educational datasets, limits the generalizability and expressiveness of…

Guided by self-determination theory and the bioecological model, this latent class analysis explores the patterns and predictors of supportive relationships in a national sample of early adolescents (N = 6,469). A six-class solution emerged: youth with (1) emotional, informational, and academic support from various adults and peers across home,…

The use of predictive analytics powered by machine learning (ML) to model educational data has increasingly been identified to exhibit bias towards marginalized populations, prompting the need for more equitable applications of these techniques. To tackle bias that emerges in training data or models at different stages of the ML modelling…