Biostatistics Commons^™

Comparative Study Of Single Imputation Techniques For The Prediction Of Missing Dairy Data, Ahmed M. Gad Prof, Ahmed Abdelhakim Ahmed Mr, Eman Manaa Prof, Basant Shafik Dr, Sakr Mostafa Prof

Business Administration

Dairy farm records are a crucial component of effective livestock business management. Record analysis allows a farm’s owner to make informed decisions. Incomplete records are less useful for data analysis, so it's important to handle missing values correctly. This study compares different imputation methods for handling missing values in a dataset of dairy records comprising 997 records collected from 234 cows between 2012 and 2022. The dataset was screened against records with missing values and then deleted, resulting in 858 observations from 200 animals. There were missing values in two variables, with a missing percentage of 13.9%: days in milk …

A New Robust Imputation Method For Longitudinal Data With Non-Normal Continuous Outcomes, Ahmed M. Gad Prof, Yasmie A. Mohamed, Nesma M. Daewish Dr, Abdelnaser S. Abdrabou Prof, Wafaa M. Ibrahim Dr

Business Administration

Missing values is very common in longitudinal data and it is the main challenge in analysis of longitudinal data. Missing values have a significant effect on longitudinal data analysis because they lead to loss of information, biased estimates, and misleading results. In practice there is a need for an imputation method to deal with missing values.

Aim: In this study a new robust regression-based imputation method to deal with missing values in longitudinal data is proposed. This method utilizes the modified adaptive linear regression model and does not require the normality of the responses. It is a novel robust imputation …

Association Between Lifetime Interpersonal Violence And Post– Covid-19 Condition Among Women In Kentucky, 2020-2022, Ayşe Güler, Heather M. Bush, Katie Schill, Nurlan Kussainov, Ann L. Coker

Biostatistics Faculty Publications

Objective: The COVID-19 pandemic increased the risk of interpersonal violence. We investigated the association between lifetime interpersonal violence experience and risk of post–COVID-19 condition (the persistence of symptoms of COVID-19 and severity of health problems associated with COVID-19 that last a few weeks, months, or years) among women with lifetime interpersonal violence experience.   Methods: Women participants aged ≥18 years in Kentucky’s Wellness, Health & You—COVID-19 study completed online quantitative surveys about the impacts of the pandemic, developing COVID-19, and symptoms of post–COVID-19 condition. We conducted cross-sectional analyses estimating rate ratios of developing COVID-19 and symptoms of post–COVID-19 condition during the …

Temporal Network Analysis Of Comorbidities Among People With Hiv In South Carolina, Yunqing Ma, Matthew Lohman Ph.D., Monique J. Brown Ph.D., Mph, Yichen Li, Xiaoming Li Ph.D., Bankole Olatosi Ph.D., Jiajia Zhang Ph.D.

Faculty Publications

Introduction: People with HIV experience a high rate of comorbidities that can complicate their health outcomes. Understanding the prevalence, interrelationships and temporal development of these comorbidities is crucial for improving health management and quality of life for people with HIV. Methods: We used a population-based cohort extracted from statewide electronic health record (EHR) data in South Carolina (SC), including 18 649 people with HIV who survived at least 1 year after HIV diagnosis between January 1, 2005, and December 31, 2020. Comorbidities and organ systems were classified using ICD-10 codes. Network analysis was performed to assess the closeness centrality among …

Highest Risk Density Region For The Communication Of The Impact Of A Treatment Covariate On The Time-To-Event Distribution, Giacomo Biganzoli, Giuseppe Marano Phd, Patrizia Boracchi Phd

COBRA Preprint Series

Analysis of time-to-event (TTE) data is central to clinical research, yet conventional summary measures like the hazard ratio (HR) and restricted mean survival time (RMST) present significant challenges. The HR is often misinterpreted, and its validity depends on the frequently violated proportional hazards assumption, while the RMST is highly sensitive to the choice of time horizon. This paper introduces two novel, assumption-free estimands to address these limitations: the Highest Risk Density Region (HRDR) and the Highest Net Risk Difference Region (HNRDR).

The HRDR identifies the narrowest time interval containing a pre-specified probability mass of events, directly answering the clinical question: …

Understanding The Impact Of The Medicaid Expansion On Hospital Length Of Stay And Emergency Department Use In Kentucky, Cameron Bushling

Theses and Dissertations--Epidemiology and Biostatistics

Three related analyses were performed to try to understand the immediate effects of Medicaid expansion on hospital systems in Kentucky. Medicaid expansion led to a large, sudden increase in the number of individuals eligible for various health care needs. This sudden increase in demand for health services lead to initial hypotheses regarding hospitals’ ability to handle this demand. The first analysis examined hospital average length of stay (LOS) using a linear mixed-effects model. Length of stay was modeled longitudinally between 2013 and 2015 to determine if significant changes in the slope of LOS could be detected after expansion (2014). Separate …

Comparison Of Machine Learning Models For Colon Cancer Survival: Predictive Modeling Approach, Reuben Adatorwovor, Motolani E. Ogunsanya, Bin Huang, Richard Charnigo, Olufunmilola Abraham

Biostatistics Faculty Publications

Background: Colon cancer is a leading cause of cancer-related deaths worldwide, with survival influenced by risk factors, treatment type, and patient characteristics. Traditional statistical models, such as Kaplan-Meier curves, have been widely used to estimate survival probabilities. However, these models often have difficulty handling complex interactions, covariates, and nonlinear relationships between risk factors. Recently, machine learning (ML) techniques have emerged as promising tools for improving survival prediction by handling large covariates and capturing complex patterns.

Objective: This study compares several ML models to accurately estimate colon cancer survival by leveraging data from the Kentucky Cancer Registry. By identifying key risk …

Disentangling The Inverse Relationship Between Cancer And Alzheimer’S Or Parkinson’S Disease: A Systematic Review On Mendelian Randomization Studies, Khine Zin Aung, Su Su Zin, Xian Wu, Zin W. Myint, Shama D. Karanth, Steven Estus, Christopher M. Norris, Peter T. Nelson, David W. Fardo, Erin L. Abner, Yuriko Katsumata

Biostatistics Faculty Publications

Introduction

Although studies have reported an inverse relationship between cancer and neurodegenerative diseases such as Alzheimer's disease (AD) and Parkinson's disease (PD), findings remain inconsistent. Observational studies are limited by survival bias and reverse causation. To better understand the relationship, we conducted a systematic review of Mendelian randomization (MR) studies examining both directions—assessing cancer as a risk factor for AD or PD, as well as AD or PD as exposures influencing cancer risk.

Methods

We systematically reviewed MR studies investigating the causal relation between cancer and either AD or PD. Cancer could be specified as either an exposure or an …

Incident Atherosclerotic Cardiovascular Disease Among Veterans By Gender Identity: A Cohort Study, Carl G. Streed Jr., Meredith S. Duncan, Kory R. Heier, T. Elizabeth Workman, Lauren B. Beach, Guneet K. Jasuja, Hill L. Wolfe, Landon D. Hughes, John R. O’Leary, Melissa Skanderson, Joseph L. Goulet

Biostatistics Faculty Publications

Background: Transgender and gender diverse (trans) populations are at elevated risk for atherosclerotic cardiovascular disease (ASCVD).

Objective: Measure the association of gender identity and gender-affirming hormone therapy (GAHT) with ASCVD outcomes.

Design: Cohort study.

Participants: Over 1 million veterans receiving care in the Veterans Health Administration.

Main Measures: Gender identity was identified via a validated natural language processing (NLP) algorithm. Incident ASCVD (acute myocardial infarction, ischemic stroke, or revascularization after the baseline date) was identified via International Classification of Diseases diagnosis codes among veterans without prevalent ASCVD. We calculated sample statistics stratified by gender identity and used Cox proportional hazard …

Adverse Childhood Experiences, Depression And Subjective Cognitive Decline By Gender: A Moderated Mediation Analysis, Monique J. Brown, Darlingtina K. Esiaka, Jaya Viswanathan

Behavioral Science Faculty Publications

Studies assessing depression as a mediating factor between adverse childhood experiences (ACEs) and subjective cognitive decline (SCD) are lacking. Therefore, the aims of this study were to: (1) determine the mediating role of depression in the association between ACEs and SCD; and (2) assess the moderating role of gender. Data were obtained from the 2023 Behavioral Risk Factor Surveillance Study (BRFSS) survey (N = 38,600). Crude and adjusted path analyses were used to determine the mediating role of depression between ACEs and SCD. Adjusted analyses controlled for sociodemographic confounders. ACEs were positively associated with depression (B = 0.129, p …

Model-Free Organization Of Patient Reported Outcomes Data: Geometrical Rep-Resentation Of The Modified Compartmen-Talization Method, Manasi Sheth, N. Rao Chaganty

Mathematics & Statistics Faculty Publications

There is a recent advancement in the field of mathematics and statistics to understand the geometry or connectedness of the data due to the massive amounts of data being generated. The data provided for analyses are usually very large and need to be organized and minimized in order to make it more useful and meaningful. In biostatistics or medical field, it is important for patients to have access to high-quality, safe and effective and/ or efficacious medical products. It is quite necessary to ascertain that the patients and their care-partners stay at the center of the regulatory decision-making process. In …

Hymate: A Hybrid Mamba And Transformer Model For Ehr Representation Learning, Md Mozaharul Mottalib, Thao-Ly Phan, Rahmatollah Beheshti

Department of Medicine Faculty Papers

Electronic health Records (EHRs) have become a cornerstone in modern-day healthcare. They are a crucial part for analyzing the progression of patient health; however, their complexity, characterized by long, multivariate sequences, sparsity, and missing values-poses significant challenges in traditional deep learning modeling. While Transformer-based models have demonstrated success in modeling EHR data and predicting clinical outcomes, their quadratic computational complexity and limited context length hinder their efficiency and practical applications. On the other hand, State Space Models (SSMs) like Mamba present a promising alternative offering linear-time sequence modeling and improved efficiency for handling long sequences, but focus mostly on mixing …

Methods In Statistics, Machine Learning, And Deep Learning For Combining Multi-Omics Dataset, Md Mutasim Billah

Dissertations, Master's Theses and Master's Reports

Transcriptome-wide association studies (TWAS) have emerged as a powerful strategy to bridge genome-wide association studies (GWAS) with gene regulatory mechanisms by integrating genotypic data with gene expression data. While early TWAS methods typically rely on linear models and single-tissue expression references, recent advances underscore the need for flexible, multi-tissue approaches that can capture heterogeneous regulatory architectures and tissue-specific expression patterns. This dissertation introduces a three‑part research project that advances multi‑tissue transcriptome‑wide association studies (TWAS) along complementary axes of methodology, statistical power, and modelling flexibility.

In chapter One, TWAS‑CTL introduces a two‑stage cross‑tissue learner that trains any user‑chosen single‑tissue imputers (STLs) …

Comparative Efficacy Of Hallucinogens In Treating Mood Disorders Through A Meta-Analysis Of Symptom Reduction, Dosage, And Duration, John Marco D.F. Muniz

Honors Undergraduate Theses

Background: Hallucinogens including psilocybin, lysergic acid diethylamide (LSD), ketamine, N,N-dimethyltryptamine (DMT) (as ayahuasca), have re-emerged as potential rapid-acting treatments for mood disorders. We conducted a meta-analysis of placebo-controlled trials evaluating their efficacy in depression and anxiety disorders. Methods: A systematic review identified 12 trials (Total ≈ 670) meeting inclusion criteria (randomized, placebo-controlled). Data on Cohen’s d and Hedges’ g effect sizes for depression- and anxiety-related outcomes were extracted. We computed pooled effect sizes (weighted by sample size and inverse variance), performed subgroup analyses by drug, diagnosis, follow-up duration, and outcome measure type, and assessed heterogeneity (I², Q …

Maternal Vulnerability Index And Severe Maternal Morbidity, Nansi S. Boghossian, Joshua Radack, Molly Passarella, Ciaran S. Phibbs, Lucy T. Greenberg, Jeffrey S. Buzas, George R. Saade, Jeannette Rogowski, Scott A. Lorch

Faculty Publications

Importance: Few studies have investigated the association of composite measures of neighborhood social determinants of health with severe maternal morbidity (SMM), and no research has examined this association for indices tailored to maternal health. Objective: To examine the association of scores in the Maternal Vulnerability Index (MVI), a tool developed to measure maternal risk of adverse health outcomes, with SMM. Design, Setting, and Participants: This retrospective, population-based cohort study was conducted in 5 states (2008-2020 for Michigan, Oregon, and South Carolina; 2008-2018 for Pennsylvania; and 2008-2012 for California) among individuals delivering a fetal death or a live birth between 22 …

Caregiving Burdens Of Task Time And Task Difficulty Among Paid And Unpaid Caregivers Of Persons Living With Dementia, Matthew Lee Smith, Jodi L. Southerland, Malinee Neelamegam, Gang Han, Shinduk Lee, Chung Lin Kew, Juanita Dawne R. Bacsu, Elyse Couch, Steffi M. Kim, Monique J. Brown Ph.D., Mph, Ayse Malatyali, Lucas Wilson, Zahra Rahemi, Jeremy Holloway, Marcia G. Ory

Faculty Publications

Background: Demands of caregivers of persons living with dementia (PLWD) are often influenced by the context of their caregiving situation. This study examines common and unique factors associated with caregiving burden in terms of task time and task difficulty among paid and unpaid caregivers of PLWD. Methods: Cross-sectional baseline survey data were analyzed from 107 paid and unpaid caregivers of PLWD participating in a larger NIH-funded study assessing the feasibility of using a novel in-situ sensor system. Oberst Caregiving Burden Scale constructs of task time and task difficulty served as dependent variables. Two least squares regression models were fitted, controlling …

Investing In The Development Of The Next Generation Of Mch Leaders, Karen A. Mcdonnell, Jamal Percy, Lisa Anders, Monique J. Brown Ph.D., Mph, Alice R. Richman, Julianna Deardorff, Monica S. Ruiz, Jihong Liu Sc.D., Kelli Russell, Audrey Snyder, Cassondra Marshall

Faculty Publications

The public health landscape is constantly evolving to address the strengths and needs of the community. Training for the public health workforce is leading the way, establishing an ecosystem approach that integrates individuals within social, political, and environmental contexts to promote health equity within a framework of social justice. One area of public health that is innovatively preparing the next generation of leaders is maternal and child health (MCH). In the United States, key indicators of health disparities within MCH remain stagnant, highlighting the need for training programs that develop future MCH professionals from diverse backgrounds. These professionals will deliver …

Healthcare Providers’ Perspective On Hiv Testing And Hypothetical Mhealth-Connected Linkage To Care Among Men Who Have Sex With Men (Msm) In South Carolina, Tony Brown, Prince Nii Ossah Addo, Monique J. Brown Ph.D., Mph, Xiaoming Li, Oluwafemi Adeagbo

Faculty Publications

Background: HIV continues to be an important public health concern in South Carolina (SC). However, an examination of providers’ willingness to use mHealth technologies to address ongoing barriers to HIV care and prevention strategies, particularly among men who have sex with men (MSM) is currently lacking in SC. We therefore explored HIV care providers’ perceptions of HIV testing and treatment uptake among MSM, and providers’ willingness to use mHealth technology to address barriers to HIV testing and treatment in SC. Methods: Between August and December 2021, we conducted semistructured virtual interviews with 10 HIV care providers recruited purposively based on …

Sars-Cov-2 Detection And Persistence In A Remote Amazonian Settlement, Glauco M. Silva, Roberto C. Ilacqua, Franciely G. Gonçalves, Carla M. Santana, Felipe T. Jordão, Paula R. Prist, Melissa S. Nolan Ph.D., Mph, Andreia F. Brilhante, Marcia A. Sperança, Gabriel Z. Laporta

Faculty Publications

Background: COVID-19 continues to pose a major global health challenge. Despite its geographic distance from Brazil’s major urban centers, Acre state has experienced notable outbreaks. This study assessed the detection and persistence of SARS-CoV-2 in the rural settlement of Santa Luzia, located in the remote municipality of Cruzeiro do Sul, Acre state, Brazil. Methods: In July 2022, a cross-sectional survey was conducted at 40 sites from an ongoing environmental study, selected by deforestation patterns and proximity to health posts. Saliva samples were collected from residents aged 5–90 years, followed by nucleic acid extraction and multiplex RT-qPCR for SARS-CoV-2 detection. Results: …

Theoretical Foundations And Applied Performance Of Periodicity-Aware Imputation: Variable Bandpass Block Bootstrap Methods For Incomplete Time Series, Asmaa Ahmad

Electronic Theses & Dissertations (2024 - present)

Time series data are prevalent across a wide range of disciplines, including health surveillance, public policy, and environmental monitoring. In the presence of underlying cyclical patterns, the integrity of time series analysis depends critically on the ability to detect, model, and impute structured missing data without compromising the temporal structure. This dissertation introduces and validates a novel imputation framework that integrates the Variable Bandpass Periodic Block Bootstrap (VBPBB) into multiple imputation procedures, improving the accuracy, robustness, and interpretability of time series models under high rates of missingness and noise. The overarching goal of this dissertation was to develop and evaluate …

Food Insecurity Among Graduate Students At The University Of Alabama At Birmingham, Amy Elizabeth Callahan

All ETDs from UAB

College food insecurity (FI) has grown steadily as a field of research over the past fifteen years. Existing research primarily has demonstrated that FI is a persistent problem with various risk factors and myriad potential impacts on students, though graduate students are largely understudied in favor of undergraduate and aggregated student populations. Given the unique circumstances graduate students face, as well as expected demographic differences such as age and household characteristics, this is a serious gap in the literature. This dissertation aims to investigate graduate student food insecurity in the United States, and particularly at the University of Alabama at …

An Adaptive Method For Covariate Balancing In Block Randomized Clinical Trials, Ren Rasnick

Theses and Dissertations

Clinical trials are randomized in part to limit allocation bias, but also to ensure comparability between treatment arms for a baseline variable of concern. Comparable with regard to a baseline variable of concern is necessary for the validity of statistical methods. However, comparability is not guaranteed for trials of any size and is even more likely in trials with < 200 total participants. We propose a new method for adapting the allocation of participants in a sequentially allocated two-armed study with a small sample size to better ensure comparability.

The proposed method calculates the expected final imbalance (lack of comparability) based on the current participant values. Unlike several other methods, our method ensures the final desired sample size for each treatment arm, utilizes the expected final imbalance, increases comparability between …

Investigating Risk Of Suboptimal Hiv Treatment Outcomes (Treatment Failure And Disengagement) Among Pregnant And Postpartum Women Living With Hiv, Kevin Owuor

All ETDs from UAB

The joint United Nations Programme on HIV/AIDS (UNAIDS) has set targets to end the HIV epidemic by improving HIV diagnosis, treatment, and viral suppression to reduce new infections and improve health outcomes for people living with HIV (PLHIV), including pregnant and postpartum women living with HIV (PPWH). After diagnosis, linking PPWH to antiretroviral (ART) treatment is critical to suppress the virus and prevent mother-to-child transmission (MTCT) of HIV. Continuous engagement in care is essential for achieving and maintaining virologic suppression in the peripartum and postpartum period for PPWH, both for their own health and the health of their family. Disengagement …

Predictive Modeling For Healthcare Data Using Nonlinear Bayesian Methods, Prince Kofi Asare

Theses and Dissertations

Unplanned hospital readmissions represent a significant challenge for healthcare systems, contributing to substantial financial burdens and highlighting gaps in patient care coordination. In the U.S., approximately 20% of Medicare beneficiaries are readmitted within 30 days, costing billions annually. Social determinants of health, such as income, housing stability, and social support, account for up to 80% of health outcomes, yet their integration into predictive models remains underexplored. This study introduces a novel Bayesian framework for predicting 30-day readmission risk, combining Gaussian Process models with spike-and-slab priors and Bayesian Lasso regression with Laplace priors. Utilizing Markov Chain Monte Carlo methods, the approach …

Group And State-Specific Estimation In Animal Movement Models Using A Bayesian Approach, Anita Bhandari Sharma

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

This research study investigates statistical approaches for modeling the movement patterns of white-tailed deer in Louisiana using GPS tracking data. We start by classifying the latent behavioral states using a hidden Markov model (HMM) and then integrate those inferred states into a state-dependent step selection framework to evaluate the land cover preferences. Standard HMMs, however, assume the same movement patterns for all animals, overlooking the differences due to characteristics such as sex, age, breeding season, etc.

To address this limitation, we extend the modeling framework to incorporate the group-level structure defined by similar characteristics or conditions to assess whether such …

Analysis Of Cytokine Data In A Case-Control Study Of Me/Cfs, Navya Amaratunga

Electronic Theses & Dissertations (2024 - present)

This study investigated the role of cytokines in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS), a debilitating multi-system disease with unknown etiology. Using data from a case-control study (60 cases, 61 controls) previously collected by Dr. Roxana Moslehi’s lab, serum levels of 48 cytokines were analyzed. Statistical analyses, including T-tests, Wilcoxon Rank Sum tests, and logistic regression (unadjusted and adjusted for medication use), were performed to identify differences between cases and controls.

Results revealed a statistically significant difference in mean Fractalkine levels between cases and controls (p=0.031). Borderline significant differences were also observed for IL-6 (p=0.046) and MIP-1α (p=0.046). Unadjusted logistic regression …

Complex Missing Data Problems In Education Surveys, Thomas Wesley Robertson

Electronic Theses & Dissertations (2024 - present)

Missing data are a nearly universal problem in human subjects research, including in education. However, reporting and addressing missing data is an issue, despite guidelines from the APA style guide and the What Works Clearinghouse, as well as guidance from prominent statisticians on the best methods to use. Prior research conducted in 2004 and 2014 found that in the field of education, most studies do not report or address missing data. In addition, no study has looked specifically at how missing data are reported and addressed in complex surveys. The current study has two main objectives: first, to determine if …

A Two-Stage Design For Choosing Among Several Normal Treatments In Comparison With A Control: The Case Of Common, Known Variance, Samarasuriyage Sayura Sankalpa Senaratne

UNF Graduate Theses and Dissertations

A two-stage design is developed for comparing the means of multiple normally distributed treatment groups under a known common variance, with the aim of identifying the treatment with the highest mean while minimizing the expected sample size, a crucial consideration in clinical trials. The proposed methodology integrates elements of both hypothesis testing and selection procedures to achieve greater efficiency and decision-making power. In the initial stage, if no treatment exhibits a mean surpassing a predefined efficacy threshold, the trial is terminated early, conserving resources. If one or more treatments exceed the threshold, the procedure advances to a second stage, where …

Hybrid Mixtures Of Factor Analyzers For High Dimensional Data, Kazeem Abiodun Kareem

Dissertations, Master's Theses and Master's Reports

Factor analysis is a powerful tool for modeling latent structures in high-dimensional data, traditional approaches assume a single global structure, limiting their ability to capture heterogeneity. The Mixture of Factor Analyzers (MFA) extends classical factor analysis by modeling data as a mixture of Gaussian-distributed local subspaces, effectively uncovering cluster-specific latent structures. However, MFA relies on Gaussian mixtures, making it sensitive to outliers and ill-suited for heavy-tailed data. The Mixture of $t$-Factor Analyzers (M$t$FA) addresses these limitations by incorporating multivariate $t$-distributions, improving robustness. Despite their advantages, both MFA and M$t$FA face significant computational challenges in high-dimensional settings, particularly due to costly …