In this work, we introduce a novel oversampling technique, the theory of inheritance and Gower distance-based oversampling (TIGO) method, designed to address class imbalance issues in mixed categorical and continuous variables data set. Drawing inspiration from genetic inheritance principles, TIGO synthesizes new minority class data,…

This dissertation documented how undergraduate students made sense of data in news media. The participants were 30 undergraduate students enrolled in a course called "Numbers and Social Justice." The study used argument analysis (Toulmin, 2003) and ethnographic methodology to examine students' written work in a naturalistic setting.…

Data are everywhere. Data collected from samples are often reported in the form of polls, medical studies, and advertisement information and an understanding of sampling distributions and statistical inference is important for evaluating data-based claims (Bargagliotti et al., 2020). Despite the importance of understanding statistical inference…

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…

Foundations of statistics research aims to establish fundamental principles guiding inference about populations under uncertainty. It is concerned with the process of learning from observations, notions of uncertainty and induction, and satisfying inferential objectives. The growing interest in predictive methods in high-stakes fields like…

Postsecondary Institutions are under pressure to explain their costs. Noninstructional administrative staff represent a significant cost and number of people working in higher education. Postsecondary institutions hire noninstructional staff in response to their specific needs related to educational activity at the institution. Past research on…

This dissertation address two significant challenges in the causal inference workflow for Big Observational Data. The first is designing Big Observational Data with high-dimensional and heterogeneous covariates. The second is performing uncertainty quantification for estimates of causal estimands that are obtained from the application of black box…

Latent change score (LCS) models are a powerful class of structural equation modeling that allows researchers to work with latent difference scores that minimize measurement error. LCS models define change as a function of prior status, which makes it well-suited for modeling developmental theories or processes. In LCS models, like other latent…

Collaborative learning provides learners with significant opportunities to collaborate on solving problems and creating better products. There has been a growing utilization of adaptive and intelligent systems to support productive learning while promoting collaborative practices. One of the core capabilities of these adaptive and intelligent…

Mixed methods research collects, analyzes, and integrates rigorous qualitative and quantitative methods to gain a deeper understanding of a phenomenon than would be gained by using either method alone. Integration is one of the key features of mixed methods research and consists of mixing qualitative and quantitative research in a systematic way…

School districts have recognized the undeniable power of using data to enhance performance. As a result, teachers are now required to use data to prepare for critical state assessments and to improve district levels. These assessments are crucial in determining the school's rating by the state and can even result in a state takeover if scores are…

Simulations were conducted to establish best practice in hyperparameter optimization and accounting for clustering in Generalized Linear Mixed-Effects Model Trees (GLMM trees). Using data-driven best practices, the relationship between a 9th Grade On-Track to Graduate (9G-OTG) indicator and observed high school graduation within four years was…

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…

Data-based decision-making has been a frequently used policy and practice intervention used in schools to help inform the decision-making processes of educational practitioners, with the aim of improving student outcomes. Interim benchmark assessments are designed by commercial test developers to support educators in this framework. In fact, the…

Public higher education in the United States (US) is funded through two primary forms: one is through state higher education appropriation funds, and the other is student financial aid that is directly given to students. Increasing postsecondary full-time equivalent (FTE) enrollment and graduation rate are becoming a crucial economic priority in…