Statistics and Probability Commons^™

Some Nonparametric Tests For High-Dimensional And Functional Data, Bilol Banerjee

Doctoral Theses

The advancement of information technology and sciences over the last few decades has facilitated the collection, storage and analysis of huge data sets. Many of these data sets contain observations having large number of features, and in some cases, this number is comparable to or even much larger than the sample size. Many traditional statistical methods cannot be meaningfully used in such situations. We develop some inferential tools for such high dimensional data. In particular, we consider the two-sample problem and the problem of testing spherical symmetry of a multivariate distributions. We construct some nonparametric tests in these contexts and …

The Nature Of Anthropogenically Driven River Drying: Spatiotemporal Causes And Consequences, Eliza Inez Gilbert

Biology ETDs

Streambed drying naturally occurs in over 60% of rivers and streams worldwide. Climate change and human regulation of surface and groundwater have increased drying in naturally intermittent systems and caused perennial systems to transition to intermittency, impacting water security, water quality, and biodiversity. To understand human-induced drying dynamics, we used 12 years of daily drying data along a 154-km regulated reach of the Rio Grande. We conceptualized river drying as a regime analogous to the natural flow regime paradigm and quantified drying magnitude, rate of change, and duration. Although linear models predicting drying magnitude and rate of change were uninterpretable, …

Towards Scalable Taxi Demand Prediction, Yifei Shen

Lingnan Theses (MPhil & PhD)

Accurate taxi demand prediction is essential for optimizing urban mobility systems across varying spatial-temporal resolutions and data conditions. Scalable taxi demand prediction refers to the capability of forecasting models to adapt to different granularities of spatial and temporal data while maintaining prediction accuracy, a critical requirement for practical urban applications ranging from fleet management to transportation planning. However, two fundamental challenges impede this scalability: data sparsity and multi-resolution forecasting requirements. Data sparsity, particularly pronounced in high-resolution predictions where numerous regions exhibit minimal activity, significantly compromises model performance. Concurrently, different urban applications necessitate predictions at varying temporal and spatial granularities, requiring …

An Experimental Investigation Of Federal Messaging On Public Support For Enforcement- And Treatment-Based Approaches For Opioid Overdose Prevention In South Carolina, Lídia Gual-Gonzalez, Hunter M. Boehme, Peter Baker, Melissa Nolan Ph.D., Mph

Faculty Publications

Background

As the opioid overdose crisis continues to produce excessive morbidity and mortality in the United States, government agencies have applied various approaches to prevent overdoses, including law-enforcement efforts (e.g., arresting people who use drugs, interrupting drug traffickers, etc.) and treatment-based approaches (e.g., naloxone, medications for opioid use disorder, etc.). Public perception and support of these approaches are relevant for informing policy, allocating resources, and effectively implementing community interventions to prevent drug-related harms.

Methods

Using an embedded informational survey design, we experimentally assessed whether public support for strategies to prevent overdose in South Carolina is influenced by language from federal …

The Sodium-Glutamate Antagonist Riluzole Improves Outcome After Acute Spinal Cord Injury: Results From The Riscis Randomised Controlled Trial Analysed Using A Global Statistical Analytic Technique, Michael G. Fehlings, Karlo M. Pedro, Mohammed Ali Alvi, Ali Moghaddamjou, James S. Harrop, Ralph Stanford, Jonathon Ball, Bizhan Aarabi, Paul M. Arnold, James D. Guest, Shekar N. Kurpad, James M. Schuster, Ahmad N. Nassr, Karl M. Schmitt, Jefferson R. Wilson, Darrel S. Brodke, Faiz U. Ahmad, Albert Yee, Wilson Z. Ray, Nathaniel P. Brooks, Jason Wilson, Diana S.L. Chow, Elizabeth G. Toups, Kevin E. Thorpe, Jiaxin Huang, Peng Huang

School of Medicine Faculty Publications

Background: Spinal cord injury (SCI) clinical trials typically rely on a single primary endpoint to assess drug efficacy. This strategy fails to adequately capture the full impact of treatment in heterogenous neurological conditions like SCI. A more patient-centric analysis requires assessment of neurological function, functional capacity, and quality of life, incorporating meaningful patient-reported outcomes. The global statistical test (GST) addresses this challenge using a unified statistical conclusion regarding the superiority of a treatment strategy over another by evaluating multiple trial endpoints simultaneously. Methods: The RISCIS trial (Safety and Efficacy of Riluzole in Acute Spinal Cord Injury Study) data was analysed …

Three-Stage Latent Dynamics Forecasting (T-Ldf) Framework For Shenzhen Metro Passenger Flow Prediction, Tianze Zhang

Lingnan Theses (MPhil & PhD)

Accurate forecasting of metro passenger flow is vital for efficient urban transportation management and optimal resource allocation in modern cities. Traditional ARIMA-based models effectively capture regular, cyclical patterns but struggle with sudden, nonlinear fluctuations caused by random events such as weather disruptions, special events, or service interruptions. Moreover, existing research predominantly focuses on individual stations, overlooking the complex cross-station interactions inherent in networked metro systems where passenger flows are interconnected across the entire network.

To address these critical limitations, we propose the Three-Stage Latent Dynamics Forecasting (T-LDF) Framework, a novel approach that systematically integrates temporal decomposition, latent dynamics extraction, and …

Secondary Malignancies In Patients With Meningioma: A Surveillance, Epidemiology, And End Results Data Analysis, Maxwell W. Pickles, Thomas Z. Rohan, Shreya Vinjamuri, Nikolaos Mouchtouris, Roger Murayi, David P. Bray, James J. Evans

Department of Neurosurgery Faculty Papers

BACKGROUND: The risk of secondary primary malignancies (SPMs) in meningioma patients is not well understood. In this unidirectional analysis, we evaluated the risk of SPMs occurring following a primary diagnosis of meningioma.

METHODS: The Surveillance, Epidemiology, and End Results (SEER-17) database (2000-2020) was used to identify 124,769 meningioma patients from a total of 9,208,295 cancer cases. Standardized incidence ratios (SIRs) were calculated using SEER's statistical analysis package to evaluate SPM risk. Basic demographic and treatment information was collected as well.

RESULTS: Of the 124,769 patients, 11,411 (9.2%) received diagnoses of an SPM, which correlates to a higher risk than the …

Predicting Sleep And Sleep Stage In Children Using Actigraphy And Heartrate Via A Long Short-Term Memory Deep Learning Algorithm: A Performance Evaluation, Robert Weaver Med, Phd, James White, Olivia Finnegan, Hongpeng Yang, Zifei Zhong, Keagan Kiely, Catherine Jones, Yan Tong, Srihari Nelakuditi, Rahul Ghosal, David E. Brown, Russell R. Pate Ph.D., Gregory J. Welk, Massimiliano De Zambotti, Yuan Wang, Sarah Burkart, Elizabeth L. Adams Phd, Bridget Armstrong, Michael Beets Med, Mph, Phd

Faculty Publications

Children's ambulatory sleep is commonly measured via actigraphy. However, traditional actigraphy measured sleep (e.g., Sadeh algorithm) struggles to predict wake (i.e., specificity, values typically < 70) and cannot predict sleep stages. Long short-term memory (LSTM) is a machine learning algorithm that may address these deficiencies. This study evaluated the agreement of LSTM sleep estimates from actigraphy and heartrate (HR) data with polysomnography (PSG). Children (N = 238, 5–12 years,52.8% male, 50% Black 31.9% White) participated in an overnight laboratory polysomnography. Participants were referred be-cause of suspected sleep disruptions. Children wore an ActiGraph GT9X accelerometer and two of three consumer wearables(i.e., Apple Watch Series 7, Fitbit Sense, Garmin Vivoactive 4) on their non-dominant wrist during the polysomnogram. LSTM estimated sleep versus wake and sleep stage (wake, not-REM, REM) using raw actigraphy and HR data for each 30-s epoch. Logistic regression and random forest were also estimated as a benchmark for performance with which to compare the LSTM results. A 10-fold cross-validation technique was employed, and confusion matrices were constructed. Sensitivity and specificity were calculated to assess the agreement between research-grade and consumer wearables with the criterion polysomnography. For sleep versus wake classification, LSTM outperformed logistic regression and random forest with accuracy ranging from 94.1to 95.1, sensitivity ranging from 94.9 to 95.9 across different devices, and specificity ranging from 84.5 to 89.6. The addition of HR improved the prediction of sleep stages but not binary sleep versus wake. LSTM is promising for predicting sleep and sleep staging from actigraphy data, and HR may improve sleep stage prediction.

Exact Sampling Of The Six-Vertex Model Using Coupling From The Past, Malaeka Amir

DePaul Discoveries

This paper aims to explore the six-vertex model through simulations designed to investigate the behavior of configurations under specific domain wall boundary conditions. To generate random configurations, we employ the Markov Chain Monte Carlo method while addressing the challenge of mixing times by utilizing the Coupling from the Past (CFTP) algorithm. Implemented in Python, our approach leverages CFTP to ensure exact sampling, avoiding the uncertainty of convergence in traditional Monte Carlo methods. We explore the monotonicity property within this framework and prove that it is only maintained by the steps of this algorithm for very particular values of the parameters.

Unified Hybrid Censoring Samples From Power Pratibha Distribution And Its Applications, Mahmoud Mansour, Hebatalla H. Mohammad Dr, Khalaf S. Sultan Prof.

Basic Science Engineering

This paper suggests an extensive inferential method for the Power Pratibha Distribution (PPD) under Unified Hybrid Censoring Schemes (UHCSs), since there is a growing interest in flexible models in both reliability and service operations. This work studies the PPD model using standard Maximum Likelihood Estimation methods and modern Bayesian approaches too. Using a complex architecture, UHCS simulates tests more closely to what is done in practice than by using more basic censoring schemes. Using analysis, the probability and statistical ranges are carefully calculated for the parameters. Tests demonstrate that Bayesian estimation gives better results than many other methods for estimation, …

Effects Of Fair Workweek Laws On Labor Market Outcomes, Joseph Pickens, Aaron Sojourner

Upjohn Institute Working Papers

This paper models fair workweek regulations that require employers to provide employees with (1) schedule predictability via advance notice of their work schedule and premium payments for short-notice changes, and (2) access to hours meaning they must offer open hours to existing employees before hiring new workers. We develop a theoretical model of employers’ responses to these provisions and their implications for employment. Guided by the model, we estimate the effects of recently-adopted fair workweek regulation in New York City’s fast-food sector using a synthetic difference-in-differences design. We find a null employment effect.

Dice Math And Probability, Warren Campbell

SEAS Faculty Publications

The manufacture of dice for tabletop games is a billion-dollar industry. In gaming circles and online forums, the concept of “cursed dice” is a popular topic. Dice are inherently unfair due to the difficulty of manufacturing them with perfect geometric tolerances and uniform material densities. A common method for testing dice fairness is the chi-square statistic, which is typically assumed to follow the chi-square distribution. However, this assumption is only asymptotically valid.

Exact distributions of the statistic can be computed for dice with few sides and a limited number of rolls—such as 2-sided (D2) and 4-sided (D4) dice—but the computational …

Syntax-Enhanced Boundary-Aware Named Entity Recognition Model, Chuanming Yu, Bin Deng, Zhengang Zhang

Journal of Scientific Information Research

[Purpose/significance] This study addresses the issue of inadequate perception of entity boundaries in traditional character-level modeling-based named entity recognition models by integrating syntax information containing entity boundary features into the task using a multi-head graph attention network with dense connections. This integration enhances the effectiveness of named entity recognition.

[Method/process] This study proposes a Syntax-enhanced Boundary-aware Named Entity Recognition Model (SynBNER), which utilizes BERT for text semantic representation and integrates syntax information using a dense-connected graph attention network. This integration incorporates implicit entity boundary information from syntax information into word representations, thereby enhancing the model's entity boundary perception capability.

[Result/conclusion] …

Advancing Statistical Methods For Multivariate And Network Meta-Analysis, Yifei Wang

Statistical Science Theses and Dissertations

Multivariate meta-analysis (MMA) and network meta-analysis (NMA) are essential tools for synthesizing evidence across multiple correlated outcomes and treatments. However, these tools face practical challenges, including outcome reporting bias (ORB), unreported within-study correlations, and computational burden. ORB can distort effect estimates in MMA, while missing within-study correlations in multivariate NMA may lead to biased conclusions. To address these challenges, this dissertation introduces two novel statistical methods. For MMA, we propose SemiMMA, a semiparametric and scalable approach that treats ORB as a missing-not-at-random problem and combines inverse propensity weighting (IPW) with the generalized method of moments (GMM). For multivariate NMA, we …

Post-Selection Inference In Regression Models, Qinyan Shen

Theses and Dissertations

This dissertation develops new methodology for valid statistical inference following model selection in various regression settings. We first consider the logistic regression model for a binary response that can only be observed at the group level, as in group testing, and is subject to testing error. With the true responses only partially observed, we employ the expectation-maximization (EM) algorithm to account for missing information in the response data and simultaneously conduct variable selection using the LASSO-penalized log-likelihood function. After variable selection, we extend an existing post-selection inference method based on the polyhedral lemma \parencite{lee2016exact} to make inferences on selected covariates, …

Methods And Applications For Bayesian Semiparametric Survival Analysis, Zile Zhao

Theses and Dissertations

Survival analysis is a cornerstone of biomedical and clinical research and plays an important role in fields as diverse as engineering, actuarial science, and sociology. In this dissertation, we develop new semiparametric Bayesian methodology for three problems from survival analysis: 1) adjustment for treatment crossover in randomized controlled trials (RCTs), 2) multilevel modeling of clustered survival outcomes when the cluster size is also informative, and 3) divide-and-conquer Bayesian inference for massive survival data. Our methods are semiparametric in the sense that we assume the covariates have a linear effect with regard to the log-hazard or the log- survival time; however, …

Spatio-Temporal Modeling & Goodness Of Fit Testing For Ecological Fire Data, Jedidiah Olof Lindborg

Theses and Dissertations

An analysis of fire data sets resulting from controlled burns was performed. Spatio-temporal models were applied to the data sets to determine which covariates are significant in predicting fire temperature. The data sets were censored and only contain temperatures above 300C, due to a limitation in the measuring device. To handle the censoring, an extrapolation was used to reconstruct the temperatures below 300C. Models were created and run for a data set with the extrapolated temperatures and a data set with all censored temperatures removed. Several aspects of the model were evaluated, such as the chosen hyperparameters, the spatial covariance …

Regression With Atypical Data: Measurement Error, Periodicity, And Non-Normality, Nicholas W. Woolsey

Theses and Dissertations

Regression is a ubiquitous and fundamental method that can be found in any ele- mentary statistics course. The simplicity and self evidently useful nature of linear regression beguiles a non-negligible portion of researchers into disrespecting assump- tions required by these models, namely in terms of accuracy of covariates and the underlying nature of the data. This disregard can at best lead to meaningless results and at worse cause significant misunderstandings in scientific pursuit.

In this dissertation we strive propose remedies to violations of specific assump- tions. Namely the assumptions that covariates are either observed without measure- ment error or they …

Functional Data Analysis On Life Expectancy And Healthcare Expenditure, Hagen Sanchez

Theses and Dissertations

This study analyzes the life expectancy for 237 countries from 1950-2023 and the healthcare expenditure for 50 countries from 1970-2022, and how life expectancy and healthcare expenditure relate to each other. Functional Principal Components Analysis was used to analyze the life expectancy and healthcare expenditure for each of the countries. Additionally, the regions of the countries were analyzed to identify any regional trends for the life expectancy data. Due to missing data and the structure of the healthcare data, multiple imputation methods and Principal Component Analysis techniques were explored for the healthcare data. Furthermore, a simulation study was conducted to …

Autoregressive Modeling Of Dna Molecule Shapes Accompanied By An Empirical Assessment Of The Ljung-Box Test, David William Custer

Theses and Dissertations

The assumption of independence rarely holds in real-world data. Correlated observations are ubiquitous, especially in sequential contexts where time series models are essential for capturing temporal dependence. This study analyzed six groups of damaged and undamaged DNA sequences, where an "F" in the middle of a sequence indicates damage. One biological aim is to understand how DNA regenerates with the assistance of proteins that recognize damaged regions. Motivated by empirical support for AR(2) modeling, we fit autoregressive models to the first three principal component scores of each DNA group, capturing the dominant structure in the data. We conducted model diagnostics, …