Statistics and Probability Commons^™

Variable Selection For High-Dimensional Data With Interaction Effects: Methods, Applications, And Inferences, Leiyue Li

Theses and Dissertations--Statistics

For high-dimensional data where the number of variables greatly exceeds the number of observations, selecting important variables while maintaining the required heredity conditions can be challenging. This dissertation is structured into three interconnected parts. In the first part, we propose a variable selection method by implementing a well-known optimization technique, the Genetic Algorithm. An R package was developed to simplify the implementation and usage of the proposed method. We then propose another variable selection method by extending the study from the Genetic Algorithm to a different but related optimization technique, Simulated Annealing. We consider three different hierarchical structures in both …

High-Dimensional Tests And Projection Methods: Subvector Analysis And Matrix Variate Data, Shouryya Mitra

Theses and Dissertations--Statistics

In this dissertation, we study projection-based methods to testing problems for high-dimensional data. We also investigate inferential methods for matrix variate data with block compound symmetry (BCS) covariance structure. The research reported in dissertation consists of three projects.

The first project addresses power loss and ill-conditioned error covariance estimates commonly faced by multivariate tests in high-dimensional settings. To overcome these challenges, previous approaches avoided correlations in constructing test statistics, but this required strong assumptions about covariance matrices and dependence structures. More recently, some methods have incorporated correlations by employing random projection into a lower-dimensional space. We develop a unified framework …

Estimation And Testing Of Nonparametric Effects Of Incomplete Multivariate And Repeated Measures Data, Swetalina Maity

Theses and Dissertations--Statistics

In this dissertation, we investigate three distinct but interrelated problems in analyzing repeated measure data with missing values.

The first project is on semiparametric methods for analyzing repeated measures designs with missing values. A closed-form estimator for the parameters and their asymptotic covariance are derived using block partitioning based on the missing data pattern. We also derive the asymptotic distribution of the estimators and construct test statistics to test hypothesis formulated as linear contrasts of the mean vector.

In the second project, we focus on purely nonparametric methods. In this setup, nonparametric treatment effects are defined as functionals of the …

From Non-Parametric Methods To Self-Supervised Learning: Applications In Edge Detection And Image Denoising, Jiacheng Xu

Theses and Dissertations--Statistics

This dissertation explores advanced methodologies for edge detection and image denoising through the application of both traditional non-parametric methods and modern self-supervised deep learning techniques. Beginning with non-parametric approaches, we refine surface fitting and jump detection criteria to enhance the detection of discontinuous regression surfaces in grayscale images. These foundational techniques are extended to color images, with analyses across RGB and CIELAB color spaces to improve edge detection accuracy. We then introduce a self-supervised neural network model that integrates Masked Modeling into the Bi-Directional Cascade Network (BDCN) framework. This approach shows the potential of reducing the dependency on annotated data …

Patterns Into Pathways For Improving Safety Culture: Refined Latent Class Analysis Informs Tailored Decision Support For South Carolina Dss Safety Culture Improvements, Michaela Voit

Theses and Dissertations--Public Health (M.P.H. & Dr.P.H.)

The rising prevalence of exposures to adverse childhood experiences (ACEs) demands a coordinated public health response, as a significant body of research details the cumulative impact of ACEs on chronic morbidities contributing to reduced life expectancy. Child welfare workers (CWW) are embedded in this public health effort, tasked with preventing and mitigating the impacts of ACEs through family and prevention services. The National Partnership for Child Safety (NPCS) may improve the wellbeing of CWWs and the effectiveness of Child Welfare (CW) services by improving the quality of safety culture within CW organizations. To inform NPCS quality improvement efforts, our project …

Imputation Strategies For Different Categories Of Missing Data, Karthik Chalumuri

Honors Theses and Capstones

Addressing missing data in research is crucial for ensuring the reliability and validity of study findings, yet it remains a significant challenge. This study investigates the impact of missing data on research outcomes and explores the underutilization of existing tools for managing missingness, potentially leading to gaps in critical information with tangible implications for decision-making processes (Dziura et al.).

Focusing on the different categories of missing data—Missing Completely At Random (MCAR), Missing At Random (MAR), and Missing Not At Random (MNAR)—this research examines various imputation strategies tailored to each category. Specifically, we compare the efficacy of several model-based imputation methods, …

A Case Study On Variations In Network Structure And Cross- Sector Alignment In Two Local Systems Serving Pregnant And Parenting Women In Recovery, Liza M. Creel, Yana Feygin, Madeline Shipley, Deborah Winders Davis, Tiffany Cole Hall, Chaly Downs, Stephanie Hoskins, Natalie Pasquenza, Scott D. Duncan

Biostatistics Faculty Publications

Objective: To describe network structure and alignment across organizations in healthcare, public health, and social services sectors that serve pregnant and parenting women with substance use disorder (SUD) in an urban and a rural community.

Data Sources and Study Settings: Two community networks, one urban and one rural with each including a residential substance use treatment program, in Kentucky during 2021.

Study Design: Social network analysis measured system collaboration and cross-sector alignment between healthcare, public health, and social services organizations, applying the Framework for Aligning Sectors. To understand the alignment and structure of each network, we measured network density overall …

Higher First 30-Day Dose Of Buprenorphine For Opioid Use Disorder Treatment Is Associated With Decreased Mortality, Feitong Lei, Michelle R. Lofwall, Jana Mcanich, Reuben Adatorwovor, Emily Slade, Patricia R. Freeman, Daniela Moga, Nabarun Dasgupta, Sharon L. Walsh, Rachel Vickers-Smith, Svetla Slavova

Biostatistics Faculty Publications

Objective: Buprenorphine is a medication for opioid use disorder that reduces mortality. This study aims to investigate the less well-understood relationship between the dose in the early stages of treatment and the subsequent risk of death.

Methods: We used Kentucky prescription monitoring data to identify adult Kentucky residents initiating transmucosal buprenorphine medication for opioid use disorder (January 2017 to November 2019). Average daily buprenorphine dose for days covered in the first 30 days of treatment was categorized as ≤8 mg, >8 to ≤16 mg, and >16 mg. Patients were followed for 365 days after the first 30 days of buprenorphine …

Synergetic Effects Of Democracy And Economic Development On Income Inequality And The Role Of Relative Political Capacity, Nazif Sali

CGU Theses & Dissertations

Diving into the complex dynamics of income inequality, this dissertation studies the multifaceted relationships between democracy, economic development, and inequality, placing a spotlight on the mediating influence of Relative Political Capacity (RPC). Uncovering the pivotal role of RPC as democracies advance and economies progress, this research navigates the contours of income inequality. By dissecting distinct sub-samples of OECD and non-OECD countries, nuanced insights surface. Employing robust methodologies such as ordinary least squares regressions and fixed effects analysis, I argue that targeted policies addressing inequality can not only foster inclusive economic growth but also fortify the foundations of democratic institutions. As …

Intelligent Capabilities Of Traditional Knowledge Organization Methods, Xinning Su

Journal of Scientific Information Research

[Purpose/significance]By analyzing the system and rules of traditional knowledge organization methods, the intelligent capabilities of traditional knowledge organization methods are refined and integrated into artificial intelligence（AI） technology, to enhance the precision and efficiency of AI in information processing. [Method/process]This paper reviews the development of knowledge organization and analyses the inherit structure and mechanisms of traditional knowledge organization methods. [Result/conclusion]Research suggests that over centuries of development and evolution, knowledge organization has gained the ability to reflect knowledge systems and disciplinary systems across different disciplines from diverse perspectives, establish semantic relations from diverse knowledge associations, and associate and integrate knowledge of different …

A Quantitative Analysis Of Seaplane Accidents From 1982-2021, David C. Ison

International Journal of Aviation, Aeronautics, and Aerospace

This study aimed to assess and analyze all historical National Transportation Safety Board accident reports since 1982. For analysis, reports were bisected into seaplane (float, amphibian, and hull) and non-seaplane groups. Findings showed that there is a deficiency in the level of available detail on the seaplane fleet and cadre of seaplane pilots in the U.S. During the most recent ten years of complete data (2012-2021) showed a negative trend in all accidents and fatal accidents, although only the latter being statistically convincing. During this timeframe, seaplane accident pilots had significantly higher total time and age than other groups (non-seaplane …

Bar-Code Variable: A Novel Approach To Efficiently Find Interaction Effects, Lee Sak Park

Theses and Dissertations--Statistics

This paper introduces the bar-code variable, a novel method for processing a sequence of binary explanatory variables efficiently in the linear regression modeling framework. Represented as an integer or a sequence of bits, the bar-code variable captures infor- mation on original binary variables and their potential interaction effects. Utilizing the bar-code variable, the study explores streamlined feature selection in linear re- gression modeling with binary explanatory variables. The paper demonstrates how the bar-code variable, through re-parameterization, facilitates the transition from cell means estimates, µ̂, in the cell-means ANOVA model to coefficient estimates, β̂, in the linear regression model, and vice …

On Generative Models And Joint Architectures For Document-Level Relation Extraction, Aviv Brokman

Theses and Dissertations--Statistics

Biomedical text is being generated at a high rate in scientific literature publications and electronic health records. Within these documents lies a wealth of potentially useful information in biomedicine. Relation extraction (RE), the process of automating the identification of structured relationships between entities within text, represents a highly sought-after goal in biomedical informatics, offering the potential to unlock deeper insights and connections from this vast corpus of data. In this dissertation, we tackle this problem with a variety of approaches.

We review the recent history of the field of document-level RE. Several themes emerge. First, graph neural networks dominate the …

Difs And Bayescluster: Novel Methods For Single_Cell Rna Sequencing Analysis, Kun Liu

Theses and Dissertations--Statistics

Single-cell RNA sequencing (scRNA-seq) has transformed our understanding of cellular heterogeneity and gene expression dynamics. Despite its potential, the inherent noise and sparsity of scRNA-seq data pose significant challenges in clustering cells into biologically meaningful groups. This dissertation addresses these challenges through two novel methodologies aimed at enhancing the accuracy and robustness of scRNA-seq data analysis.

First, we introduce the Differential Feature Selection (DIFS) framework, designed to improve the identification of differential features in scRNA-seq data. DIFS employs a two-stage marker identification process. In the first stage, a modified Dip Test is used to filter and identify genes with significant …

A Case Report On A Women’S Residential Substance Use Program In A Rural And Urban Setting, Deborah Winders Davis, Yana Feygin, Madeline Shipley, Tiffany Cole Hall, Chaly Downs, Stephanie Hoskins, Natalie Pasquenza, Scott D. Duncan, Liza M. Creel

Biostatistics Faculty Publications

Purpose To describe program characteristics and outcomes of a residential substance use recovery program serving pregnant and parenting women in a rural and urban location.

Description This assessment of administrative records from April 1, 2020 through March 31, 2022, included women in a rural (n = 140) and urban (n = 321) county in Kentucky.

Assessment This retrospective case study used descriptive and non-parametric analyses to assess the population and examine differences between locations, race, and ethnicity for women served. Logistic regression tested predictors of goal achievement by community. Of 461 women served, 65 (14.1%) delivered a baby while in …

Health Care For People Who Are Incarcerated: Teaching Third-Year Medical Students About Rights, Challenges, And Avenues Of Advocacy, Anna-Maria South, Kelsey N. Karnik, Sara Hieneman, Anthony A. Mangino, Michelle R. Lofwall

Biostatistics Faculty Publications

Introduction: Incarcerated patients are a vulnerable patient population with unique barriers to health care that physicians in every specialty encounter. Current medical school curricula lack universal education on health care for incarcerated people.

Methods: We developed an interactive workshop to provide third-year medical students at the University of Kentucky with information about delivering care outside of dedicated carceral settings to individuals who are incarcerated. The workshop included education on the demographic characteristics and medical conditions present in these populations along with understanding incarcerated persons’ rights to health care and how to interact with them and the associated jail/prison workforce often …

Contrastive Learning, With Application To Forensic Identification Of Source, Cole Ryan Patten

Electronic Theses and Dissertations

Forensic identification of source problems often fall under the category of verification problems, where recent advances in deep learning have been made by contrastive learning methods. Many forensic identification of source problems deal with a scarcity of data, an issue addressed by few-shot learning. In this work, we make specific what makes a neural network a contrastive network. We then consider the use of contrastive neural networks for few-shot learning classification problems and compare them to other statistical and deep learning methods. Our findings indicate similar performance between models trained by contrastive loss and models trained by cross-entropy loss. We …

Generating Neutrosophic Random Variables Based Gamma Distribution, Maissam Ahmad Jdid, Florentin Smarandache, Khalifa Al Shaqsi

Branch Mathematics and Statistics Faculty and Staff Publications

In practical life, we encounter many systems that cannot be studied directly, either due to their high cost or because some of these systems cannot be studied directly. Therefore, we resort to the simulation method, which depends on applying the study to systems similar to real ones and then projecting these results if they are suitable for the real system. The simulation process requires a good understanding of probability distributions and the methods used to transform random numbers that follow a regular distribution in the field [0,1] into random variables that follow them, so that we can achieve the greatest …

Row-Column Designs: A Novel Approach For Analyzing Imprecise And Uncertain Observations, Abdulrahman Alaita, Muhammad Aslam, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

Classical row-column designs cannot be applied when the underlying data set contains some imprecise, uncertain, or undetermined observations. In this paper, we discuss row-column design under a neutrosophic statistical framework. A significant contribution of our study is to propose a novel approach to analyzing row-column designs using neutrosophic data. This approach involves calculating the neutrosophic analysis of variance (NANOVA) table for the proposed design and using it to derive the FN -test in an uncertain environment. Two numerical examples have been used to assess the proposed design’s performance. Results from the study indicated that a row column design under …

Examining Information Systems Use To Facilitate The Workplace Accommodation Process, Shiya Cao

Statistical and Data Sciences: Faculty Publications

BACKGROUND: The workplace accommodation process is often affected by ineffective and inefficient communications and information exchanges among disabled employees and other stakeholders. Information systems (IS) can play a key role in facilitating a more effective and efficient accommodation process since IS has been shown to facilitate business processes and effect positive organizational changes.

OBJECTIVE: Since there is little to no research that exists on IS use to facilitate the workplace accommodation process, this paper, as a critical first step, examines how IS have been used in the accommodation process.

METHODS: Thirty-six interviews were conducted with disabled employees from various organizations. …