The elevated rates of failure, dropout, and withdrawal (FDW) in introductory statistics courses pose a significant barrier to students' timely graduation from college. Identifying actionable strategies to support instructors in facilitating student success by reducing FDW rates is paramount. This thesis undertakes a comprehensive approach, leveraging various machine learning algorithms to address this pressing issue. Drawing from three years of data from an introductory statistics course at one of the largest universities in the USA, this study examines the problem in depth. Numerous predictive classification models have been developed, showcasing the efficacy of machine learning techniques in this context. Actionable insights gleaned from these statistical and machine learning models have been consolidated, offering valuable guidance for instructors. Moreover, the complete analytical framework, encompassing data identification, integration, feature engineering, model development, and report generation, is meticulously outlined. By sharing this methodology, the aim is to empower researchers in the field to extend these approaches to similarly critical courses, fostering a more supportive learning environment. Ultimately, this endeavor seeks to enhance student retention and success, thereby contributing to the broader goal of promoting timely graduation from college.

The deleterious effects of not completing high school in the United States and around the world in the current monetary, societal, and employment climate make efforts toward increasing graduation rates an imperative. The impetus for educational reform for improving graduation rates is even more salient for students with disabilities who graduate at lower rates than their peers without disabilities (Stetser & Stillwell, 2014). To provide the multi-tiered systems of support (MTSS) necessary to engage in this reform, data-systems with accurate and timely information are necessary. This research included construction of Hierarchical Generalized Linear Models to investigate the individual- and school-level predictor variables associated with on-time high school graduation for students with disabilities. To that end, the research examined the relationships among (1) individual student demographic background variables (2) individual academic and behavioral school related variables (3) school-wide characteristics of the schools that students in the research study attended and (4) on-time graduation as defined by the Federal Uniform Graduation Rate criteria. This research revealed significant relationships between on-time graduation and individual-level variables for students with disabilities including grade point average, attendance, and primary disability labels of Autism Spectrum Disorder and Intellectual Disabilities across grade levels. Additional significant predictors were found at specific grade levels (e.g., socio-economic status and education in a more restrictive environment). Implications for research to practice include a focus on early intervention prior to high school to increase odds of on-time graduation for students with disabilities and inclusion of additional variables for students with disabilities in Early Warning Systems (EWS). Additionally, customizing EWS through analysis of predictor sensitivity for specific populations by school district or school was discussed.