Statistics and Probability Commons^™

Factors Affecting Pedestrian-Vehicle Conflicts: An Empirical Analysis, Christo D. Jamo

Honors Scholar Theses

The number of pedestrian deaths increased by 78% between 2009 and 2023, while other motor vehicle crash deaths increased by 13% in the same period [1]. To identify potential pedestrian safety measures, this study analyzed the effects of location-based demographics, pedestrian phasing type, and other physical infrastructure and behavior variables on the probability of pedestrian-vehicle conflicts at signalized intersections, which is a surrogate measure of crash risk. Data were collected from 55 intersections in Connecticut, and the pedestrian-vehicle interactions were classified by severity based on the Swedish Traffic Conflict Technique: undisturbed passage, potential conflict, minor conflict, or serious conflict. Because …

A Novel Approach To Creativity Assessment: Forced Pairwise Ranking With Large Language Models, Phillip R. Gregory Jr

Master's Theses

Assessing creativity at scale remains a persistent challenge in cognitive science, as human raters are costly, slow, and often inconsistent in their judgments. This thesis introduced a novel framework for automated scientific creativity assessment using forced pairwise ranking, in which fine-tuned large language models compared response pairs and determined which was more creative. Five empirical studies were conducted using Llama-2-7B and Llama-2-13B models adapted via LoRA fine-tuning and benchmarked against human scored responses from the Scientific Creative Thinking Test. A regression baseline achieved Pearson �� = .74 on the test set, matching the human inter-rater ceiling reported in the literature. …

Pattern Dynamics And Stochasticity Of Brain Rhythms And Spike Trains In A Tauopathy Mouse Model Of Alzheimer’S Disease, Clarissa M. Hoffman

Dissertations and Theses (Open Access)

Systems neuroscience posits that every aspect of perceived physical reality, every aspect of animal and human behavior, and every cognitive phenomenon emerges from patterns of neuronal activity. While most researchers embrace this idea, there are major difficulties in describing and analyzing these complex neuronal dynamics—spike flows produced by cells ensembles, synchronized extracellular field oscillations, and other patterns—which limits our understanding of how the activity of individual neurons and the whole-animal cognition and behavior might be connected. In particular, we lack the approaches and even the semantics for connecting the individual cell outputs and the integrated results of their activity. Current …

Best Linear Unbiased Prediction Based On Optimally Selected Order Statistics Using Compound Design, Foster Nkansah

Open Access Theses & Dissertations

Any life-testing experiments with censoring generate ordered failure data, which are used to estimate model parameters of the underlying lifetime distribution. However, predicting unobserved failure times is an important goal post inference. Balakrishnan and Bhattacharya [2021] showed that joint best linear unbiased predictors (BLUPs) are more efficient than their marginal counterparts. In this thesis, we introduce a compound optimal design to compute joint BLUPs based on a suitably chosen subset of the observed data. It is shown that the linear predictors of the parameters from any location-scale distribution, based on a few optimally chosen ranks, obtained from the compound optimal …

Log Anomaly Detection With Parameter-Efficient Tiny Language Models: From Centralized Fine-Tuning To Privacy-Preserving Federated Learning, Isaiah Thompson Thompson Ocansey

Open Access Theses & Dissertations

System logs are a primary source of information for identifying faults, misconfigurations, and security incidents in computing infrastructure. As these logs grow in volume and complexity, manual inspection becomes impractical, and automated detection methods are needed. This thesis investigates how compact language models can be applied to the task of log anomaly detection under two operational conditions: when log data is centralized and when it is located at different data sites.

In the first part, we propose LogTinyLLM, which applies parameter-efficient fine-tuning through Low-Rank Adaptation and adapter-based techniques to adapt tiny language models for identifying contextual anomalies in log sequences. …

Contamination-Aware Boosting For Cancer Prediction, Francis Opoku

Open Access Theses & Dissertations

Modern cancer research increasingly relies on machine learning methods to model complex relationships between high-dimensional genomic predictors and clinically relevant outcomes. Gradient boosting methods, particularly XGBoost, have become widely used due to their strong predictive performance and ability to capture nonlinear effects and interactions. However, these methods are sensitive to contamination in the data, especially in the response variable, where even a small fraction of aberrant observations can disproportionately influence model fitting and degrade generalization.

In this thesis, we propose a contamination-aware extension of XGBoost, termed CA-XGBoost, which improves robustness by explicitly modeling residuals through a latent mixture framework. This …

An Ordinal Categorical Data Analysis Using The Stereotype Model Within A Bayesian Framework With A Logistic-Normal Prior, Nathaniel A. Sakyi

Open Access Theses & Dissertations

Ordinal categorical data are pervasive in applied research, yet their analysis is often compromised by modeling strategies that implicitly assume equidistant category spacing or impose restrictive structural constraints. Metric regression models and latent-variable threshold approaches routinely misrepresent ordinal information, leading to biased inference, distorted uncertainty quantification, and loss of structural insight. This paper develops a Bayesian framework for ordinal regression that explicitly accommodates \textbf{unequal spacing among ordered response categories} while preserving ordinal structure and interpretability.

The proposed approach builds on the stereotype regression model, which embeds ordinal categories into a latent one-dimensional continuum through estimable score parameters. While the stereotype …

A Diagnostic Test For Confounding Under Collapsibility In Generalized Linear Models (Glms), Samuel Dela Gadah

Open Access Theses & Dissertations

This thesis develops and validates a diagnostic framework for assessing potential confounding in generalized linear models (GLMs) with collapsible link functions. Under collapsibility and effect homogeneity, the absence of confounding implies equality between marginal and covariate-adjusted treatment effects on the link scale, which motivates the change-in-estimate parameter δ = γ − γ(c) as the target of a formal hypothesis test. Two complementary inferential routes are developed: a nonparametric bootstrap and an independent estimating equation (IEE) procedure based on a stacked-data construction that yields a closed-form sandwich variance and is implementable in standard generalized estimating equation software. A backward elimination procedure …

Deep Neural Network-Gaussian Process For Housing Price Analysis, Bismark Nyarko

Open Access Theses & Dissertations

Neural networks have demonstrated remarkable predictive performance in complex, high-dimensional settings. However, their highly parameterized structure and nonlinear architecture often make them difficult to interpret, limiting formal statistical inference and principled uncertainty quantification. In contrast, Gaussian processes (GPs) provide a fully probabilistic framework with a relatively small number of hyperparameters, enabling coherent uncertainty quantification and seamless integration into hierarchical and structured statistical models. Despite their theoretical flexibility as nonparametric function approximators, standard GP formulations frequently exhibit weaker predictive performance than modern neural networks in large-scale applications.

In this work, we employ a Gaussian process covariance function designed to approximate the …

Riemannian Manifold-Coupled Joint Sparse Graphical Models For Spatially Structured Precision Matrix Estimation, Abdul Rahman Adam

Open Access Theses & Dissertations

This thesis introduces a novel geometry-aware framework for joint precision matrix estimation in spatially structured data. Unlike existing joint Gaussian graphical model estimators that rely on Euclidean coupling mechanisms such as fused or group graphical lasso, our approach incorporates intrinsic Riemannian geometry through geodesic distance penalties on the symmetric positive definite manifold.

The method measures similarity between precision matrices of adjacent spatial regions using the affine-invariant Riemannian distance, capturing deformations of concentration ellipsoids rather than entrywise differences. This is particularly suited for spatial transcriptomics, where regions may share dependence structures despite differences in scale or composition.

An efficient Alternating Direction …

High Throughput Phenomics Pipeline For Pulse Crop Nutritional Breeding, Amod Udayanga Madurapperumage

All Dissertations

Dry pea (Pisum sativum L.), lentil (Lens culinaris Medik.), and chickpea (Cicer arietinum L.) are major pulse crops valued for their high nutritional composition and importance to global food systems. Pulses are rich in carbohydrates, protein, and essential minerals, making them ideal whole foods and critical contributors to food and nutrition security. Due to these advantages, pulse breeding programs are increasingly focusing on enhancing nutritional traits, such as protein quality, amino acid balance, and micronutrient density, through the process of biofortification. However, improvement of agronomic traits remains equally essential. Characteristics such as plant height, standability, stress tolerance, …

Constraint-Aware Metaheuristic Optimization For Experimental Design, Benjamin N. Fuller

All Graduate Theses and Dissertations, Fall 2023 to Present

Designing experiments becomes much more challenging when many variables and strict constraints are involved, as is common in modern science and engineering. This thesis introduces a new computational and mathematical framework that efficiently searches for optimal experiments in complex, high-dimensional spaces where traditional methods fail. By combining geometric techniques with flexible optimization algorithms like particle swarm optimization, our methods handle difficult constraints while scaling to real-world problems. Built in the high-performance Julia programming language and released as open-source software, this work bridges advanced theory with practical tools, offering researchers a powerful and accessible way to design better experiments under realistic …

Scalable Roof Polygon Extraction And Geometric Characterization From Remotely-Sensed Data For Snow Load Assessment, Jashon Newlun

All Graduate Theses and Dissertations, Fall 2023 to Present

Heavy snow accumulation on rooftops is a serious structural risk in cold climates, and understanding how much snow builds up on different types of roofs is essential for safe building design. Currently, most data on roof snow loads comes from small, labor-intensive field surveys that cover only a handful of buildings at a time. This results in far too few measurements of buildings to draw confident conclusions about how snow behaves across communities. This thesis develops and demonstrates a new automated approach for measuring roof snow accumulation and extracting key building characteristics across thousands of buildings at once using airborne …

A New Approach To Generate Combinatorial Patterns In Logical Analysis Of Data And Its Application To Predict College Retention, Salihah Ahmed E. Jaafari

Theses and Dissertations

Student retention and degree completion remain central challenges for higher-education institutions, with significant implications for student success, institutional effectiveness, and public accountability. While advances in predictive analytics have enabled earlier identification of students at risk of withdrawal, many commonly used machine learning approaches suffer from limited interpretability, constraining their practical usefulness for advising, intervention, and policy decision making. This dissertation addresses the problem of predicting student persistence by developing and evaluating optimization based, interpretable classification models within the Logical Analysis of Data (LAD) framework. Building on existing LAD formulations, this research introduces two novel pattern generation models, the Best Term …

Feasibility Study Of Transitioning From Thick Plates (0.250”) Mounted On 30-Point Pvc Carriers To Thinner Plate Technologies Mounted On Recyclable Foam And Pet (0.155”) For Post-Print Corrugated, Nathaniel J. Poole

All Theses

In the United States, the most common press configuration for brown-box printing is a 0.280” undercut press. These press configurations have long relied on thick 0.250” plates mounted on 0.030” PVC sheets to print onto corrugated substrates. Each year, around twenty million pounds of waste are produced by the printing industry, through paper waste, plate waste, among other materials. One large factor of that waste is flexographic plate waste, which either ends its life in a landfill or is repurposed into other products. This study establishes a comparison between traditionally used 0.250” plates on 30pt PVC versus 0.155” plates mounted …

Research Remix: Teams, Tech, And Texts, Jaime Carbajal

UNLV Best Teaching Practices Expo

The pedagogical innovation that enhanced student learning in the Research Methodologies in Health Sciences course is described as Integrated Digital Collaborative Inquiry-Based Learning (IDCIBL). The IDCIBL approach leveraged digital tools (lecture videos, podcasts, recorded poster presentations, and Artificial Intelligence (AI) platforms), integrated journal article analysis, utilized research-informed active learning, and included team-based learning activities. The combination of multiple innovative strategies into the IDCIBL model intentionally transforms the educational environment and optimizes the student learning experience, relating to the TLC priority area of teaching and assessments in the age of Gen AI.

Coexistence Of“Emotion”And“Rationality”：Analysis Of The Impact Mechanism Of Frequent Reversal Events On The Evolution Of Online Public Opinion, Liqiang Wang, Xueqi Li, Yixian Wang

Journal of Scientific Information Research

[Purpose/significance] In recent years, frequent reversal events have negatively impacted the online media environment, leading to an increasing number of skeptical voices during the evolution of public opinion.These doubts are no longer merely emotional outbursts but also involve rational understanding of the event's authenticity. This study aims to gain a deeper understanding of this phenomenon and attempts to reveal the impact mechanism of frequent reversal events on the evolution of online public opinion. [Method/process] Through surveys and computer simulation experiments, the study analyzes various elements such as individuals, media environment, and evolution patterns in online public opinion,then according to the …

The Item Response Warehouse: What It Is, How To Use It, And Targets For Potential Improvements, Savira D. Nadela, Hansol Lee, Nishka Jain, Ayaan Gupta, Xingyi Zhang, Benjamin W. Domingue

Chinese/English Journal of Educational Measurement and Evaluation | 教育测量与评估双语期刊

The Item Response Warehouse (IRW) is a repository of harmonized item response datasets designed to support secondary analysis and methodological research in psychological and educational measurement. This paper serves as a practical guide for researchers interested in using the IRW. We describe the structure of IRW datasets and the quantitative and qualitative metadata available for dataset selection, and we demonstrate how researchers can navigate the IRW website to explore and compare available tables. We further show how the IRW R and Python packages can be used to filter datasets programmatically, download response-level data, and generate standardized citations for reproducible research …

Ma(1) Or White Noise?, Orithea Regn, Ferebee Tunno

Create@State

This project provides an over of testing an MA(1) process confidence interval while keeping the margin of error to a minimum, even for small sample sizes.

Simulation And Projection Of Glaciers And Their Runoff In Xinjiang Based On Tgsgs, Zhongqin Li, Yefei Yang, Bowen Liu, Huilin Li, Zexin Zhan, Feiteng Wang, Chunhai Xu, Weibo Zhao

Bulletin of Chinese Academy of Sciences (Chinese Version)

Glaciers are large flowing ice bodies formed from snowfall in cold regions. Due to the intrinsic physical properties of ice and the complexity of boundary conditions, physically based modelling of glacier change remains a global challenge. With support from the Chinese Academy of Sciences’ key science infrastructure program for the field station, the Tianshan Glaciological Station completed the Tianshan Glacier Station Glacier Simulator (TGSGS) in 2025. TGSGS features advanced representations of the physical mechanisms driving glacier change and multi-scale ensemble strategy, and is integrated with a reference glacier observation network based on terrestrial laser scanning (TLS), a low-temperature laboratory for …