Vision classification tasks, a fundamental and transformative aspect of deep learning and computer vision, play a pivotal role in our ability to understand the visual world. Deep learning techniques have revolutionized the field, enabling unprecedented accuracy and efficiency in vision classification. However, deep learning models, especially…

Collecting data for the purpose of decision making has become an integral part of the landscape of education in the United States over the past decade. Many educators are swamped with such an overwhelming amount of information that it can be difficult to sort and analyze, leaving them floundering under wave after wave of data. The SWIS facilitator…

One of the most significant issues in education, as defined by the U.S. Department of Education Office of Accountability (2018), is disproportionality in exclusionary discipline. Disproportionality is defined as the over- and under-representation of racial/ethnic minorities in relation to their overall enrollment (Ahram et al., 2011). Currently,…

Digital learning environments are becoming increasingly ubiquitous as a wide range of EdTech products and services enter classrooms and households across the globe. One salient attribute of these environments is their capacity to generate large amounts of data as students interact with the technology. These data logs can help construct a detailed…

Decision-making, a key factor of organizational performance, is based on information retrieved from processing raw data. As businesses and consumers are shifting toward digital channels, more and more data is being generated through digital services and electronic devices. Big Data is argued to have significant benefits to businesses, and yet data…

Digital phenotyping is defined as the "moment-by-moment quantification of the individual level human phenotype in situ using data from personal digital devices". The passive data collected by smartphone devices, including GPS, accelerometer and communication logs, can provide insights on users' behaviors that could be related to various…

This qualitative case study sought to discover how school-level data teams can intentionally use effective data practices to identify and implement high-leverage interventions that support all students, including Black and Latinx boys, in attaining the necessary academic requirements for high school graduation. The researcher analyzed data from…

This action research study investigates the role of Data-Based Decision-Making (DBDM) in increasing academic outcomes within a charter school network. During Cycle 1, interviews and focus groups with teachers, interventionists, and school deans shed light on critical themes, including leadership, data collection, analytic capacity, and a culture…

Most higher education institutions in the United States would not be able to answer, "how many LGBTQ+ students are at your school?" Rarely are colleges and universities asking students to self-identify their sexual or gender identity, leading to disconnect with the community, gaps of information, and difficulty with outreach. The purpose…

This dissertation is composed of projects on three aspects of gathering and learning from data in the social sciences: drawing representative samples, taking valid measurement, and making warranted inductive inferences. Chapter one studies the challenge of drawing representative human samples. It is well documented that most samples used by…

The purpose of this dissertation is to understand the impacts of social service data collection and use on the lives of young people and those that serve them, and to offer ways for youth, nonprofits, and funders to positively evolve these systems. It grew from three simple questions without clear answers: what's happening, how's it working, and…

Missing values that fail to be appropriately accounted for may lead to reduced statistical power, biased estimators, reduced representativeness of the sample, and incorrect interpretations and conclusions (Gorelick, 2006). The current study provided an ontological perspective of data manipulation by explaining how statistical results can…

Elementary school teachers struggle to collect and use reading progress data to make instructional decisions. Collecting and interpreting reading progress data when making instructional decisions allows districts to identify and support students who need early reading intervention and may protect districts from Free Appropriate Public Education…

Research conducted at scientifically significant sites produces an abundance of important and highly valuable data. Yet, though sites are logical points for coordinating the curation of these data, their unique needs have been under supported. Previous studies have shown that two principal stakeholder groups -- scientific researchers and local…

This study examined the effects of John Kotter's Eight Steps for Successful Change framework and strategies in systems implementation in a secondary educational environment. Teachers' perceptions of the effectiveness of Kotter's strategies used by their administrative team to support positive change were examined. The study evaluated data provided…