Learning is a multimodal process, and learning analytics (LA) researchers can readily access rich learning process data from multiple modalities, including audio-video recordings or transcripts of in-person interactions; logfiles and messages from online activities; and biometric measurements such as eye-tracking, movement, and galvanic skin…

This study explores the potential to enhance the performance of convolutional neural networks (CNNs) for automated scoring of kinematic graph answers through data augmentation using Deep Convolutional Generative Adversarial Networks (DCGANs). By developing and fine-tuning a DCGAN model to generate high-quality graph images, we explored its…

In this paper, we investigate the conditions under which data imbalances, a common data characteristic that occurs when factor values are unevenly distributed, are problematic for the performance of Coincidence Analysis (CNA). We further examine how such imbalances relate to fragmentation and noise in data. We show that even extreme data…

This case study examines employee attrition, its detrimental effects on businesses, and the potential of data analytics to address this challenge. By employing Latent Dirichlet Allocation (LDA), a sophisticated NLP technique, we delve into the underlying reasons for employee departures. Additionally, we explore using RapidMiner to develop…

Supervision models are fundamental to our supervision practices and criticized for lacking empirical support. As a data-driven approach based on research with expert supervisors, Cohesive Model of Supervision unifies existing models' central premises in a meaningful manner and emphasizes the understated areas of supervision practice.

This paper discusses the "how" of conducting participatory research that engages youth as participants and, more importantly, as co-researchers. In collaboration with four community co-researchers, this arts-based inquiry engaged 14 young Black people ranging in age from seven to fifteen years around their definitions of joy. Using a…

This study aims to suggest a generalized class of estimators for population proportion under simple random sampling, which uses auxiliary attributes. The bias and MSEs are considered derived to the first degree approximation. The validity of the suggested and existing estimators is assessed via an empirical investigation. The performance of…

This study presents several multivariate Generalizability theory designs for analyzing automatic item-generated (AIG) based test forms. The study used real data to illustrate the analysis procedure and discuss practical considerations. We collected the data from two groups of students, each group receiving a different form generated by AIG. A…

Sport analytics remains a growing area in the sport industry. As such, the demand for skills and knowledge in this area has grown. This demand includes off-field data, such as marketing trends, as well as financial data related to sport organizations. There has been a trickle-down effect in sport management (and other) education programs to teach…

This paper introduces the LEGO® Database, a large natural dataset that can be used to teach Structured Query Language (SQL) and relational database concepts. This dataset is well-suited for introductory and advanced database assignments and end-of-semester group projects. The data is freely available from Kaggle.com and contains eight tables with…

This supplement contains additional information for the report, "Support for the Journey Home: An Impact Study of the Returning Citizens Stimulus Program." The Returning Citizens Stimulus (RCS) program was a pilot program for reentry cash support and aimed to help people quickly reach stability in their lives outside of prison and reduce…

This study introduces an optimized ensemble deep neural network (Optimized Ensemble Deep-NN) to enhance the accuracy of predicting student grades. This model solves the problem of different and complicated student performance data by using deep neural networks, ensemble learning, and a number of optimization algorithms, such as Adam, SGD, and RMS…

Children's fuzziness leads to increased variance in the data, data loss, and high dropout rates in developmental studies. This study investigated the importance of 20 factors on the person (child, caregiver, experimenter) and situation (task, method, time, and date) level for the data quality as indicated via the number of valid trials in 11…

Substantial shares of eligible students forgo or lose access to tuition-free college benefits, in part due to limited access to information on eligibility and other requirements. Given students' dependence on the Internet for information on how to pay for college, we examine the availability and digital accessibility of critical program…

Despite the increasing interest in data analytics applications within postgraduate education research, there remains a significant gap in research dedicated to exploring mixed methods research for such investigations. This study undertook to bridge this gap by exploring the application and use of mixed methods research to examine data analytics…