Statistics and Probability Commons^™

Topics In Multilevel Mediation Analysis, Chung Li Wu

Theses and Dissertations

A proper study design assures adequate power to detect statistically significant differences. Existing power calculations for multilevel mediation analysis make a strong distributional assumption of normality. However, binary outcomes are commonly seen in real-world study. Motivated by this fact, we conduct a simulation-based power study for a multilevel mediation analysis with binary outcomes. The numbers of participants needed to achieve 80% power are summarized in tables for future reference.

Mixed-effect regression is commonly used in multilevel analysis for panel data. Yet, the estimated coefficients from the random-intercept model could represent either purely between-cluster, purely within-cluster, or weighted-average effects. Therefore, we …

Extensions Of Discrete Choice Experiment Theory For Public Health, Farahnaz Islam

Theses and Dissertations

A discrete choice experiment (DCE) allows researchers to understand how individuals value characteristics of a product or service in hypothetical scenarios and the trade-offs these individuals are willing to make between these characteristics. DCEs quickly gained traction in public health but as more researchers utilized DCEs in broader contexts, several methodological questions have arisen. This dissertation addresses some of these gaps in the literature.

One critique of DCEs is whether individuals would make the same choice in reality as they claimed they would have made in the hypothetical scenario. Perhaps the most efficient way to evaluate the predictive value of …

Classification Of Breast Cancer Histopathological Images Using Semi-Supervised Gans, Balaji Avvaru, Nibhrat Lohia, Sowmya Mani, Vijayasrikanth Kaniti

SMU Data Science Review

Breast cancer is diagnosed more frequently than skin cancer in women in the United States. Most breast cancer cases are diagnosed in women, while children and men are less likely to develop the disease. Various tissues in the breast grow uncontrollably, resulting in breast cancer. Different treatments analyze microscopic histopathology images for diagnosis that help accurately detect cancer cells. Deep learning is one of the evolving techniques to classify images where accuracy depends on the volume and quality of labeled images. This study used various pre-trained models to train the histopathological images and analyze these models to create a new …

Stock Forecasts With Lstm And Web Sentiment, Michael Burgess, Faizan Javed, Nnenna Okpara, Chance Robinson

SMU Data Science Review

Traditional time-series techniques, such as auto-regressive and moving average models, can have difficulties when applied to stock data due to the randomness inherent to the markets. In this study, Long Short-Term Memory Recurrent Neural Networks, or LSTMs, have been applied to pricing data along with sentiment scores derived from web sources such as Twitter and other financial media outlets. The project team utilized this approach to complement the technical indicators observed at the end of each trading day for three stocks from the NASDAQ stock exchange over a 12-year span. A common benchmark to assess model performance on time series …

Predicting Insulin Pump Therapy Settings, Riccardo L. Ferraro, David Grijalva, Alex Trahan

SMU Data Science Review

Millions of people live with diabetes worldwide [7]. To mitigate some of the many symptoms associated with diabetes, an estimated 350,000 people in the United States rely on insulin pumps [17]. For many of these people, how effectively their insulin pump performs is the difference between sleeping through the night and a life threatening emergency treatment at a hospital. Three programmed insulin pump therapy settings governing effective insulin pump function are: Basal Rate (BR), Insulin Sensitivity Factor (ISF), and Carbohydrate Ratio (ICR). For many people using insulin pumps, these therapy settings are often not correct, given their physiological needs. While …

Classification Of Pixel Tracks To Improve Track Reconstruction From Proton-Proton Collisions, Kebur Fantahun, Jobin Joseph, Halle Purdom, Nibhrat Lohia

SMU Data Science Review

In this paper, machine learning techniques are used to reconstruct particle collision pathways. CERN (Conseil européen pour la recherche nucléaire) uses a massive underground particle collider, called the Large Hadron Collider or LHC, to produce particle collisions at extremely high speeds. There are several layers of detectors in the collider that track the pathways of particles as they collide. The data produced from collisions contains an extraneous amount of background noise, i.e., decays from known particle collisions produce fake signal. Particularly, in the first layer of the detector, the pixel tracker, there is an overwhelming amount of background noise that …

Cov-Inception: Covid-19 Detection Tool Using Chest X-Ray, Aswini Thota, Ololade Awodipe, Rashmi Patel

SMU Data Science Review

Since the pandemic started, researchers have been trying to find a way to detect COVID-19 which is a cost-effective, fast, and reliable way to keep the economy viable and running. This research details how chest X-ray radiography can be utilized to detect the infection. This can be for implementation in Airports, Schools, and places of business. Currently, Chest imaging is not a first-line test for COVID-19 due to low diagnostic accuracy and confounding with other viral pneumonia. Different pre-trained algorithms were fine-tuned and applied to the images to train the model and the best model obtained was fine-tuned InceptionV3 model …

Application Of Probabilistic Ranking Systems On Women’S Junior Division Beach Volleyball, Cameron Stewart, Michael Mazel, Bivin Sadler

SMU Data Science Review

Women’s beach volleyball is one of the fastest growing collegiate sports today. The increase in popularity has come with an increase in valuable scholarship opportunities across the country. With thousands of athletes to sort through, college scouts depend on websites that aggregate tournament results and rank players nationally. This project partnered with the company Volleyball Life, who is the current market leader in the ranking space of junior beach volleyball players. Utilizing the tournament information provided by Volleyball Life, this study explored replacements to the current ranking systems, which are designed to aggregate player points from recent tournament placements. Three …

Dietary Inflammatory Index And Mortality From All Causes, Cardiovascular Disease, And Cancer: A Prospective Study, Zhen Lin, Yanfei Feng, Nitin Shivappa Mbbs, Mph, Ph.D., James R. Hébert Scd, Xin Xu

Faculty Publications

The Energy-adjusted Dietary Inflammatory Index (E-DIITM) is a comprehensive, literature-derived index for assessing the effect of dietary constituents on inflammatory biomarkers and inflammation-related chronic diseases. Several studies have examined the association between E-DII scores and mortality, with results that vary across populations. Therefore, in the present study, we aimed to investigate the potential association between E-DII scores and all-cause, cardiovascular disease (CVD), and cancer mortality using data from the Prostate, Lung, Colorectal and Ovarian (PLCO) Screening Trial. E-DII scores, calculated based on a food-frequency questionnaire, were analyzed both as a continuous variable and after categorization into quintiles. A multivariate Cox …

Availability Of Hospital-Based Cancer Services Before And After Rural Hospital Closure, 2008-2017, Whitney Zahnd Ph.D., Peiyin Hung Ph.D., Sylvia Kewei Shi, Anja Zgodic, Melinda A. Merrell Ph.D., Elizabeth L. Crouch, Janice C. Probst, Jan Eberth Ph.D.

Faculty Publications

Introduction

Rural populations have less access to cancer care services and experience higher cancer mortality rates than their urban counterparts, which may be exacerbated by hospital closures. Our objective was to examine the impact of hospital closures on access to cancer-relevant hospital services across hospital service areas (HSAs).

Methods

We used American Hospital Association survey data from 2008 to 2017 to examine the change in access to cancer-related screening and treatment services across rural HSAs that sustained hospitals over time, experienced any closures, or had all hospitals close. We performed a longitudinal analysis to assess the association between hospital closure …

Neighborhood Characteristics And Dementia Symptomology Among Community-Dwelling Older Adults With Alzheimer’S Disease, Dana M. Alhasan, Matthew C. Lohman Ph.D., Jana A. Hirsch, Margaret Chandlee Miller Ms, Ph.D., Bo Cai Ph.D., Chandra L. Jackson

Faculty Publications

Background: Neuropsychiatric symptoms (NPSs) lead to myriad poor health outcomes among individuals with Alzheimer’s disease (AD). Prior studies have observed associations between the various aspects of the home environment and NPSs, but macro-level environmental stressors (e.g., neighborhood income) may also disrupt the neuronal microenvironment and exacerbate NPSs. Yet, to our knowledge, no studies have investigated the relationship between the neighborhood environment and NPSs.

Methods: Using 2010 data among older adults with AD collected from a sample of the South Carolina Alzheimer’s Disease Registry, we estimated cross-sectional associations between neighborhood characteristics and NPSs in the overall population and by race/ethnicity. Neighborhood …

Yin And Yang Of Cannabinoid Cb1 Receptor: Cb1 Deletion In Immune Cells Causes Exacerbation While Deletion In Non-Immune Cells Attenuates Obesity, Kathryn Miranda, William Becker, Philip B. Busbee, Nicholas Dopkins, Osama A. Abdulla, Yin Zhong, Jiajia Zhang Ph.D., Mitzi Nagarkatti, Prakash S. Nagarkatti

Faculty Publications

While blockade of cannabinoid receptor 1 (CB1) has been shown to attenuate diet-induced obesity (DIO), its relative role in different cell types has not been tested. The current study investigated the role of CB1 in immune vs non-immune cells during DIO by generating radiation-induced bone marrow chimeric mice that expressed functional CB1 in all cells except the immune cells or expressed CB1 only in immune cells. CB1^-/- recipient hosts were resistant to DIO, indicating that CB1 in non-immune cells is necessary for induction of DIO. Interestingly, chimeras with CB1^-/- in immune cells showed exacerbation in DIO combined with …

Geographic Proximity To Primary Care Providers As A Risk-Assessment Criterion For Quality Performance Measures, Nathaniel Bell, Ana Lopez-De Fede Ph.D., Bo Cai Ph.D., John Brooks Ph.D.

Publications

Importance Previous studies have found a mixed association between Patient-Centered Medical Home (PCMH) designation and improvements in primary care quality indicators, including avoidable pediatric emergency department (ED) encounters. Whether these associations persist after accounting for the geographic locations of providers relative to where patients reside is unknown. Objective To examine the association between geographic proximity to primary care providers versus hospitals and risk of avoidable and potentially avoidable ED visits among children with pre-existing diagnosis of attention-deficit/hyperactivity disorder or asthma. Methods Retrospective cohort study of a panel of pediatric Medicaid claims data from the South Carolina from 2016–2018 for 2,959 …

Cardiorespiratory Fitness And The Risk Of All-Cause, Cardiovascular And Cancer Mortality In Men With Hypercholesterolemia, Xuemei Sui M.D., M.P.H., Ph.D., Mark A. Sarzynski Facsm, Nicole Gribben, Jiajia Zhang Ph.D., Carl J. Lavie

Faculty Publications

Background: Whether higher cardiorespiratory fitness (CRF) confers protection against cardiovascular disease (CVD) in individuals with manifest hypercholesterolemia is poorly understood. Methods: Participants were 8920 men aged 20–82 years with hypercholesterolemia but no history of CVD and/or cancer and who received a preventive examination at the Cooper Clinic in Dallas, TX, USA, during 1974–2001. CRF was quantified as maximal treadmill test duration and was grouped for analysis as low, moderate, or high based on the traditional Aerobics Center Longitudinal Study cutpoints. Using Cox regression analyses, we computed hazard ratios and 95% confidence intervals for risk of mortality based on CRF. Results: …

Processed Food As A Risk Factor For The Development And Perpetuation Of Crohn's Disease-The Enigma Study, Gina L. Trakman, Winnie Y.Y. Lin, Amy L. Hamilton, Amy L. Wilson-O'Brien, Annalise Stanley, Jessica Y. Ching, Jun Yu, Joyce W.Y. Mak, Yang Sun, Junkin Niu, Yinglei Miao, Xiaoqing Lin, Rui Feng, Minhu Chen, Nitin Shivappa Mbbs, Mph, Ph.D., James R. Hébert Scd, Mark Morrison, Siew C, Ng, Michael A. Kamm

Faculty Publications

(1) Background: Developing countries have experienced a rapid recent rise in Inflammatory Bowel Disease (IBD) incidence and emerging evidence suggests processed foods and food additives may predispose one to the development and perpetuation of Crohn’s disease (CD). The aim of this study was to evaluate processed food and food additive intake in CD patients and controls, in Australia (high CD incidence), Hong Kong (intermediate incidence) and mainland China (emerging incidence). (2) Methods: In 274 CD patients (CD), 82 first-degree relatives (FDR), 83 household members (HM) and 92 healthy unrelated controls (HC) from Australia (n = 180), Hong Kong (HK) (n …

Numerical Analysis Of A Second Order Ensemble Method For Evolutionary Magnetohydrodynamics Equations At Small Magnetic Reynolds Number, John Carter, Nan Jiang

Mathematics and Statistics Faculty Research & Creative Works

We study a second order ensemble method for fast computation of an ensemble of magnetohydrodynamics flows at small magnetic Reynolds number. Computing an ensemble of flow equations with different input parameters is a common procedure for uncertainty quantification in many engineering applications, for which the computational cost can be prohibitively expensive for nonlinear complex systems. We propose an ensemble algorithm that requires only solving one linear system with multiple right-hands instead of solving multiple different linear systems, which significantly reduces the computational cost and simulation time. Comprehensive stability and error analyses are presented proving conditional stability and second order in …

Combining Phenotypic And Genomic Data To Improve Prediction Of Binary Traits, Diego Jarquin, Arkaprava Roy, Bertrand S. Clarke, Subhashis Ghosal

Department of Statistics: Faculty Publications

Plant breeders want to develop cultivars that outperform existing genotypes. Some characteristics (here ‘main traits’) of these cultivars are categorical and difficult to measure directly. It is important to predict the main trait of newly developed genotypes accurately. In addition to marker data, breeding programs often have information on secondary traits (or ‘phenotypes’) that are easy to measure. Our goal is to improve prediction of main traits with interpretable relations by combining the two data types using variable selection techniques. However, the genomic characteristics can overwhelm the set of secondary traits, so a standard technique may fail to select any …

Cancer Incidence And Stage At Diagnosis Among People With Recent-Onset Psychotic Disorders: A Retrospective Cohort Study Using Health Administrative Data From Ontario, Canada., Jared C Wootten, Lucie Richard, Phillip S Blanchette, Joshua C. Wiener, Kelly K. Anderson

Epidemiology and Biostatistics Publications

OBJECTIVE: Prior evidence on the relative risk of cancer among people with psychotic disorders is equivocal. The objective of this study was to compare incidence and stage at diagnosis of cancer for people with psychotic disorders relative to the general population.

METHOD: We constructed a retrospective cohort of people with a first diagnosis of non-affective psychotic disorder and a comparison group from the general population using linked health administrative databases in Ontario, Canada. The cohort was followed for incident diagnoses of cancer over a 25-year period. We used Poisson and logistic regression models to compare cancer incidence and stage at …

Orthogonal Arrays And Legendre Pairs, Kristopher N. Kilpatrick

Theses and Dissertations

Well-designed experiments greatly improve test and evaluation. Efficient experiments reduce the cost and time of running tests while improving the quality of the information obtained. Orthogonal Arrays (OAs) and Hadamard matrices are used as designed experiments to glean as much information as possible about a process with limited resources. However, constructing OAs and Hadamard matrices in general is a very difficult problem. Finding Legendre pairs (LPs) results in the construction of Hadamard matrices. This research studies the classification problem of OAs and the existence problem of LPs. In doing so, it makes two contributions to the discipline. First, it improves …

Implementing Github Actions Continuous Integration To Reduce Error Rates In Ecological Data Collection, Albert Y. Kim, Valentine Herrmann, Ross Barreto, Brianna Calkins, Erika Gonzalez-Akre, Daniel J. Johnson, Jennifer A. Jordan, Lukas Magee, Ian R. Mcgregor, Nicolle Montero, Karl Novak, Teagan Rogers, Jessica Shue, Kristina J. Anderson-Teixeira

Statistical and Data Sciences: Faculty Publications

Accurate field data are essential to understanding ecological systems and forecasting their responses to global change. Yet, data collection errors are common, and data analysis often lags far enough behind its collection that many errors can no longer be corrected, nor can anomalous observations be revisited. Needed is a system in which data quality assurance and control (QA/QC), along with the production of basic data summaries, can be automated immediately following data collection.

Here, we implement and test a system to satisfy these needs. For two annual tree mortality censuses and a dendrometer band survey at two forest research sites, …

Biomonitoring Of Polybrominated Dioxins & Furans, Polychlorinated Dioxins & Furans, And Dioxin Like Polychlorinated Biphenyls In Vietnamese Female Electronic Waste Recyclers, Jenevieve S. Peecher, Arnold J. Schecter, Helen Lu, Hoang Trong Quynh, Arnold Stromberg, Jiaying Weng, Riley Crandall, Linda S. Birnbaum

Statistics Faculty Publications

Objective: E-waste is rising globally. This is a follow up to our study reporting metals/polybrominated diphenyl ethers (PBDE’s)/polychlorinated biphenyls (PCBs) in female e-waste recyclers. Here we report polybrominated, polychlorinated dioxins/furans, and dioxin-like polychlorinated biphenyls in these same workers. Methods: Female Vietnamese recyclers and non-recyclers recruited; blood samples collected. Polybrominated, polychlorinated dioxins/ furans, and dioxin-like polychlorinated biphenyls levels compared in recyclers, non-recyclers, and National Health and Nutrition Examination Surveys (NHANES). Results: Recyclers >non-recyclers: 12378-PBDD, 2378-TBDF, 12378-PCDF, 123478-HxCDF, 123678-HxCDF, 1234678-HpCDF, PCB-126. Non-recyclers >NHANES: 123478-HxCDF, 123678-HxCDF, 234678- HxCDF, PCB-126, PCB-169. NHANES >non-recyclers: 12378-PCDD, 123478-HxCDD, 123678-HxCDD, 123789-HxCDD, 1234678-HpCDD, 123789-HxCDF, 1234678-HpCDF, 1234789-HpCDF, OCDF, PCB-81, PCB-114, …

Fabrications And Applications Of Micro/Nanofluidics In Oil And Gas Recovery: A Comprehensive Review, Junchen Liu, Yandong Zhang, Mingzhen Wei, Xiaoming He, Baojun Bai

Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works

Understanding fluid flow characteristics in porous medium, which determines the development of oil and gas oilfields, has been a significant research subject for decades. Although using core samples is still essential, micro/nanofluidics have been attracting increasing attention in oil recovery fields since it offers direct visualization and quantification of fluid flow at the pore level. This work provides the latest techniques and development history of micro/nanofluidics in oil and gas recovery by summarizing and discussing the fabrication methods, materials and corresponding applications. Compared with other reviews of micro/nanofluidics, this comprehensive review is in the perspective of solving specific issues in …

The Microscopical Evidence Traces Analysis Of Household Dust And Its Statistical Significance As A Definitive Identification Technique, Stephanie Polifroni

Dissertations, Theses, and Capstone Projects

Evidence found at crime scenes is used to assist in creating a link the suspect, the victim, and the scene. As stated by the Locard’s Principle, every contact leaves a trace, that evidence can be used to link together an investigation. Traces are collected in hopes that they can be identified and associated to an individual or individuals to help solve that particular crime. However, the strongest conclusion for evidence traces is an association to a source, and unless a physical match of some kind is found, an individualization cannot be established even when known sample is available. However, having …

Evidence Of Likely Autochthonous Chagas Disease In The Southwestern United States: A Case Series Of Trypanosoma Cruzi Seropositive Blood Donors, Mary K. Lynn, Kyndall C. Dye-Braumuller, Norman L. Beatty, Patricia L. Dorn, Stephen A. Klotz, Susan L. Stramer, Rebecca L. Townsend, Hany Kamel, Jacquelyn M. Vannoy, Patrick Sadler, Susan P. Montgomery, Hilda N. Rivera, Melissa Nolan Ph.D., Mph

Faculty Publications

Background Chagas disease is a parasitic infection that can insidiously cause non-ischemic cardiomyopathy. Given the largely silent nature of this progressive disease, asymptomatic blood donors pose potential blood transfusion risk. Blood donation screening has become an unintentional form of Chagas disease surveillance, with thousands of new cases identified since national surveillance was initiated in 2007.

Study Design and Methods We recruited T. cruzi-positive blood donors identified from California and Arizona blood centers for confirmatory blood screening and assessment of lifetime infection risk.

Results Among eight suspected cases, we identified four confirmed US autochthonous infections. The current manuscript details the …

Analytic Case Study Using Unsupervised Event Detection In Multivariate Time Series Data, Jeremy M. Wightman

Theses and Dissertations

Analysis of cyber-physical systems (CPS) has emerged as a critical domain for providing US Air Force and Space Force leadership decision advantage in air, space, and cyberspace. Legacy methods have been outpaced by evolving battlespaces and global peer-level challengers. Automation provides one way to decrease the time that analysis currently takes. This thesis presents an event detection automation system (EDAS) which utilizes deep learning models, distance metrics, and static thresholding to detect events. The EDAS automation is evaluated with case study of CPS domain experts in two parts. Part 1 uses the current methods for CPS analysis with a qualitative …

Statistical Inference On Desirability Function Optimal Points To Evaluate Multi-Objective Response Surfaces, Peter A. Calhoun

Theses and Dissertations

A shortfall of the Derringer and Suich (1980) desirability function is lack of inferential methods to quantify uncertainty. Most articles for addressing uncertainty usually involve robust methods, providing a point estimate that is less affected by variation. Few articles address confidence intervals or bands but not specifically for the Derringer and Suich method. This research provides two valuable contributions to the field of response surface methodology. The first contribution is evaluating the effect of correlation and plane angles on Derringer and Suich optimal solutions. The second contribution proposes and compares 8 inferential methods--both univariate and multivariate--for creating confidence intervals on …

Spatial Analysis For Enhancing The Use Of Health Data Availability From Different Sources To Help The Decision-Making Process, Tris Eryando

Kesmas

Spatial analysis in public health has become a common method used by researchers to understand the distribution of public health aspects related to the surrounding environment. It can also be used to analyze individual information in the form of a dot and the location or line of aggregated information in a specific area of study. Another benefit is the possibility of using different data sources to be analyzed in one statistical model analysis, as long as the identification area is sufficiently clear as a key variable. Spatial analysis can show an object's distribution on a locational map and explain the …

Sars-Cov-2 Antibody Seroprevalence In Jakarta, Indonesia, Iwan Ariawan, Hafizah Jusril, Muhammad N Farid, Pandu Riono, Wiji Wahyuningsih, Widyastuti Widyastuti, Dwi Oktavia T L Handayani, Endang Sri Wahyuningsih, Rebekka Daulay, Retno Henderiawati, Safarina G. Malik, Rintis Noviyanti, Leily Trianty, Nadia Fadila, Khin Saw Aye Myint, Frilasita A. Yudhaputri, Neeraja Venkateswaran, Kodumudi Venkateswaran, Venkatachalam Udhayakumar, William A. Hawley, Juliette Morgan, Paul M. Pronyk

Kesmas

The SARS-CoV-2 transmission dynamics in low- and middle-income countries remain poorly understood. This study aimed to estimate the SARS-CoV-2 antibodies seroprevalence in Jakarta, Indonesia, and to increase knowledge of SARS-CoV-2 transmission in urban settings. A population-based serosurvey among individuals aged one year or older was conducted in Jakarta. Employing a multistage sampling design, samples were stratified by district, slum, and non-slum residency, sex, and age group. Blood samples were tested for IgG against three different SARS-CoV-2 antigens. Seroprevalence was estimated after applying sample weights and adjusting for cluster characteristics. In March 2021, this study collected 4,919 respondents. The weighted estimate …

A Stunting Prevention Risk Factors Pathway Model For Indonesian Districts/Cities With A Stunting Prevalence Of ≥30%, Nina Fentiana, Endang L. Achadi, Besral Besral, Abram Kamiza, Trini Sudiarti

Kesmas

The prevalence of stunting in Indonesian children aged 0-23 months is a public health problem caused by direct and indirect factors. This study aimed to discover the path of the relationship between various risk factors and the stunting prevalence of ≥30% in 165 districts/cities in Indonesia. Data were obtained from the 2018 National Basic Health Research, National Socioeconomic Survey, and the Statistics Indonesia with a cross-sectional approach. The secondary data on stunting and risk factors were aggregated at the district/city level from individual data; children aged 0-23 months. The path analysis used to determine a stunting prevention model showed that …

Determinants Of Type 2 Diabetes Mellitus Among Passive Smokers, Adinda Rahma Triyaniarta, Santi Martini, Kurnia Dwi Artanti, Sri Widati, Rizma Dwi Nastiti

Kesmas

Type 2 diabetes mellitus (T2DM) leads to complications of other diseases. The modifiable risk factors for T2DM are overweight, physical activity, hypertension, unhealthy diet, and smoking. This study aimed to analyze determinants of T2DM incidence in passive smokers among various factors. This study was conducted at Hospital X in Surabaya City, East Java Province, Indonesia, from September 2019 to April 2020. The variables were univariate, bivariate, and multivariate. Case samples were T2DM patients and passive smokers, while control samples were non-T2DM patients and passive smokers, with 52 respondents per group, of 104 total respondents. Variables statistically significant related to the …