This dissertation examined classification outcome differences among four popular individual supervised machine learning (ISML) models (logistic regression, decision tree, support vector machine, and multilayer perceptron) when predicting minor class membership within imbalanced datasets. The study context and the theoretical population sampled…

In today's era of large-scale data, academic institutions, businesses, and government agencies are increasingly faced with heterogeneous datasets. Consequently, there is a growing need to develop effective methods for extracting meaningful insights from this type of data. Quantile, expectile, and expected shortfall regression methods offer useful…

Every year, the national high school graduation rate is declining and impacting the number of students applying to colleges. Moreover, the majority of students are applying to more than one college. This makes a lot of colleges to be highly competitive in student recruitment for enrollment and thus, the necessity for institutions to anticipate…

Multivariate count data is ubiquitous in many areas of research including the physical, biological, and social sciences. These data are traditionally modeled with the Dirichlet Multinomial distribution (DM). A new, more flexible Dirichlet-Tree Multinomial (DTM) model is gaining in popularity. Here, we consider Bayesian DTM regression models. Our…

All of our choices and all that sets us apart are governed by what we can do, what we want to do, and what we know. This dissertation aims to quantify two of these channels to better understand why we differ. The first two chapters focus on what we know and how it shapes societal gaps. The first chapter attacks the question of how much of the gap…

In education, machine learning (ML), especially deep learning (DL) in recent years, has been extensively used to improve both teaching and learning. Despite the rapid advancement of ML and its application in education, a few challenges remain to be addressed. In this thesis, in particular, we focus on two such challenges: (i) data scarcity and…

Student growth percentiles (SGPs) have become a common means to measure and report on student academic growth for state education accountability, and some states have adopted SGP cutscores as a means of classifying student growth into categories like "high/medium/low" growth. It has therefore become important to understand properties of…

This meta-analysis was designed to examine the effectiveness of school-based mental health interventions. After refining search criteria, 1138 articles were returned from ERIC, EBESCO, and Psychological Behavior Science Collection. Next, article abstracts, and full text were screened to ensure each article met the study criteria before articles…

Many institutions use placement tests as a method to assess students' readiness for college-level coursework. With the increased use of technology in testing, many institutions have transitioned placement test administration to an online format in an unproctored setting. While unproctored placement tests may provide financial and logistical…

Over the last four decades, meta-analysis has proven to be a vital analysis strategy in educational research for synthesizing research findings from different studies. When synthesizing studies in a meta-analysis, it is common to assume that the true underlying effect varies from study to study, as studies will differ in design, participants,…

The purpose of this quantitative correlational predictive study aimed to assess to what extent the number of actual study table hours predicted change of Grade Point Average (GPA) for at-risk student-athletes participating in revenue and non-revenue sports. Data was collected from 108 participants total, fifty-three participants in…

Early alert systems are an intervention at community colleges that aim to identify and informally intervene with students who are struggling in their courses. This study examined the relationship between early alert systems and student success in developmental and gateway math courses. This study also examined if the impact of early alert…

Statistical association is a key facet of statistical literacy: claims based on relationships between variables or ideas rooted in data are found everywhere in media and discourse. A key development in introductory statistics curricula is the use of simulation-based inference, which has shown positive outcomes for students, especially in regards…

We study flexible Bayesian methods that are amenable to a wide range of learning problems involving complex high dimensional data structures, with minimal tuning. We consider parametric and semiparametric Bayesian models, that are applicable to both static and dynamic data, arising from a multitude of areas such as economics, finance and…

This study used a propensity score approach to estimate treatment effects in a multilevel setting. The propensity score approach involves the estimation of propensity scores for covariate balancing and the estimation of treatment effects. This study aimed at understanding how propensity scores estimated through a simple logistic regression compare…