Statistics and Probability Commons^™

484— Modeling Social Distancing Methods And Their Effectiveness In Combating The Spread Of Ebola, Rachel Fair

GREAT Day Posters

Ebola Virus Disease (EVD) is a rare but severe disease that is transmitted among humans through direct-contact with, and close proximity to, infected bodily fluids. From 2014-16, West Africa experienced the largest Ebola outbreak ever recorded, infecting over 28,000 people, and killing over 11,000. Although the symptoms of EVD are treatable, the disease can be extremely deadly, with an average of 50% EVD cases resulting in fatality. In areas where healthcare is scarce and vaccinations are not readily available, the practices of social distancing and self-quarantining have been shown to be highly effective in combating the spread of EVD. To …

465— Modeling Vaccine Efficacy For Tuberculosis In A Prison Population, Kaitlyn Mundackal

GREAT Day Posters

Tuberculosis is a highly contagious disease and is particularly problematic in confined communities such as prisons. I simulated how Tuberculosis moves through a prison population and tested how much vaccination effort is needed to control its spread. To explore this, I tested adding ever increasing numbers of randomly placed edges in a network and determined the size of the largest component. Afterwards, I removed edges in the model using two different methods, one illustrating if the edges were removed randomly and the other starting with prisoners that had the most connections, to simulate the effect of vaccination. My results show …

Universal Vector Neural Machine Translation With Effective Attention, Joshua Yi, Satish Mylapore, Ryan Paul, Robert Slater

SMU Data Science Review

Neural Machine Translation (NMT) leverages one or more trained neural networks for the translation of phrases. Sutskever intro- duced a sequence to sequence based encoder decoder model which be- came the standard for NMT based systems. Attention mechanisms were later introduced to address the issues with the translation of long sen- tences and improving overall accuracy. In this paper, we propose two improvements to the encoder decoder based NMT approach. Most trans- lation models are trained as one model for one translation. We introduce a neutral/universal model representation that can be used to predict more than one language depending on …

Demand Forecasting In Wholesale Alcohol Distribution: An Ensemble Approach, Tanvi Arora, Rajat Chandna, Stacy Conant, Bivin Sadler, Robert Slater

SMU Data Science Review

In this paper, historical data from a wholesale alcoholic beverage distributor was used to forecast sales demand. Demand forecasting is a vital part of the sale and distribution of many goods. Accurate forecasting can be used to optimize inventory, improve cash ow, and enhance customer service. However, demand forecasting is a challenging task due to the many unknowns that can impact sales, such as the weather and the state of the economy. While many studies focus effort on modeling consumer demand and endpoint retail sales, this study focused on demand forecasting from the distributor perspective. An ensemble approach was applied …

Demand Forecasting For Alcoholic Beverage Distribution, Lei Jiang, Kristen M. Rollins, Meredith Ludlow, Bivin Sadler

SMU Data Science Review

Forecasting demand is one of the biggest challenges in any business, and the ability to make such predictions is an invaluable resource to a company. While difficult, predicting demand for products should be increasingly accessible due to the volume of data collected in businesses and the continuing advancements of machine learning models. This paper presents forecasting models for two vodka products for an alcoholic beverage distributing company located in the United States with the purpose of improving the company’s ability to forecast demand for those products. The results contain exploratory data analysis to determine the most important variables impacting demand, …

An Exploration Of Link Functions Used In Ordinal Regression, Thomas J. Smith, David A. Walker, Cornelius M. Mckenna

Journal of Modern Applied Statistical Methods

The purpose of this study is to examine issues involved with choice of a link function in generalized linear models with ordinal outcomes, including distributional appropriateness, link specificity, and palindromic invariance are discussed and an exemplar analysis provided using the Pew Research Center 25th anniversary of the Web Omnibus Survey data. Simulated data are used to compare the relative palindromic invariance of four distinct indices of determination/discrimination, including a newly proposed index by Smith et al. (2017).

Data-Driven Investment Decisions In P2p Lending: Strategies Of Integrating Credit Scoring And Profit Scoring, Yan Wang

Doctor of Data Science and Analytics Dissertations

In this dissertation, we develop and discuss several loan evaluation methods to guide the investment decisions for peer-to-peer (P2P) lending. In evaluating loans, credit scoring and profit scoring are the two widely utilized approaches. Credit scoring aims at minimizing the risk while profit scoring aims at maximizing the profit. This dissertation addresses the strengths and weaknesses of each scoring method by integrating them in various ways in order to provide the optimal investment suggestions for different investors. Before developing the methods for loan evaluation at the individual level, we applied the state-of-the-art method called the Long Short Term Memory (LSTM) …

The Impact Of Pev User Charging Behavior In Building Public Charging Infrastructure, Ahmad Almaghrebi

Durham School of Architectural Engineering and Construction: Dissertations, Theses, and Student Research

Plug-in electric vehicles (PEVs) play a significant role in the development of green cities since they generate less pollution than conventional vehicles. To promote PEV adoption and mitigate range anxiety, charging infrastructure should be deployed at strategic locations that are readily accessible to the public. Nebraska is working on the expansion of charging infrastructure around the state; however, stakeholders face several difficulties in trying to minimize irregular charging behaviors. Most electric vehicle users plug in and leave their vehicles for an extended time at public parking lots designated for PEVs. Some users even leave their vehicles for longer than 24 …

Analysis Of Gas Mileage Of A Car, Joshua Ballard-Myer

Georgia College Student Research Events

The objective of this work is to analyze a data set, Auto, from the R package ISLR: Introduction to Statistical Learning in R. The data set includes information for 392 observations on 9 variables including gas mileage, horsepower, weight in pounds, and engine displacement in cubic inches. The data set was taken from the StatLib library maintained at Carnegie Mellon University. The primary response variable will be gas mileage in miles per gallon, with all other variables serving as predictors, but other relationships with other response variables such as acceleration will be explored. Results were similar to expected; traits desirable …

Personal Foul: How Head Trauma And The Insurance Industry Are Threatening Sports, Zachary Cooler

Senior Honors Theses

This thesis will investigate the growing problem of head trauma in contact sports like football, hockey, and soccer through medical studies, implications to the insurance industry, and ongoing litigation. The thesis will investigate medical studies that are finding more evidence to support the claim that contact sports players are more likely to receive head trauma symptoms such as memory loss, mood swings, and even Lou Gehrig’s disease in extreme cases. The thesis will also demonstrate that these medical symptoms and monetary losses from medical claims are convincing insurance companies to withdraw insurance coverage for sports leagues, which they are justifying …

Community Impact On The Home Advantage Within Ncaa Men's Basketball, Erin O'Donnell

Department of Statistics: Dissertations, Theses, and Student Research

The home advantage is a commonly accepted truth throughout sports performances. This paper investigates the magnitude of the home advantage among NCAA Men’s Basketball teams. It will then look to draw relationships between the magnitude of the home advantage and community aspects such as attendance, location, past program success, and social media presence. Univariate and Multivariate models will be investigated.

Advisor: Walter S Stroup

Residual-Matching: An Efficient Alternative To Random Sampling In Human Subjects Research Recruitment, Andrew Hooyman, Matthew J. Huentelman, Sydney Y. Schaefer

Kinesiology and Nutrition Sciences Faculty Research

Given the time- and resource-intense nature of human subjects research, we have developed a more intelligent approach to participant recruitment above and beyond random sampling that leverages pilot or preliminary results to reduce the overall number of participants needed for recruitment from an existing electronic cohort or database. Using open-access data from the General Social Survey (GSS) of the National Opinion Research Center, we generated pilot and validation datasets through a simulation to establish moderate and weak relationships based on linear regression. We then compared the performance of our residual-matching method against random sampling in their probabilities of achieving a …

Nonlinear Least Squares 3-D Geolocation Solutions Using Time Differences Of Arrival, Michael V. Bredemann

Mathematics & Statistics ETDs

This thesis uses a geometric approach to derive and solve nonlinear least squares minimization problems to geolocate a signal source in three dimensions using time differences of arrival at multiple sensor locations. There is no restriction on the maximum number of sensors used. Residual errors reach the numerical limits of machine precision. Symmetric sensor orientations are found that prevent closed form solutions of source locations lying within the null space. Maximum uncertainties in relative sensor positions and time difference of arrivals, required to locate a source within a maximum specified error, are found from these results. Examples illustrate potential requirements …

A Credit Analysis Of The Unbanked And Underbanked: An Argument For Alternative Data, Edwin Baidoo

Doctor of Data Science and Analytics Dissertations

The purpose of this study is to ascertain the statistical and economic significance of non-traditional credit data for individuals who do not have sufficient economic data, collectively known as the unbanked and underbanked. The consequences of not having sufficient economic information often determines whether unbanked and underbanked individuals will receive higher price of credit or be denied entirely. In terms of regulation, there is a strong interest in credit models that will inform policies on how to gradually move sections of the unbanked and underbanked population into the general financial network.

In Chapter 2 of the dissertation, I establish the …

Quasi-Likelihood Ratio Tests For Homoscedasticity In Linear Regression, Lili Yu, Varadan Sevilimedu, Robert Vogel, Hani Samawi

Journal of Modern Applied Statistical Methods

Two quasi-likelihood ratio tests are proposed for the homoscedasticity assumption in the linear regression models. They require few assumptions than the existing tests. The properties of the tests are investigated through simulation studies. An example is provided to illustrate the usefulness of the new proposed tests.

Investigating The Performance Of Propensity Score Approaches For Differential Item Functioning Analysis, Yan Liu, Chanmin Kim, Amrey D. Wu, Paul Gustafson, Edward Kroc, Bruno D. Zumbo

Journal of Modern Applied Statistical Methods

To evaluate the performance of propensity score approaches for differential item functioning analysis, this simulation study was conducted to assess bias, mean square error, Type I error, and power under different levels of effect size and a variety of model misspecification conditions, including different types and missing patterns of covariates.

Dot: Gene-Set Analysis By Combining Decorrelated Association Statistics, Olga A. Vsevolozhskaya, Min Shi, Fengjiao Hu, Dmitri V. Zaykin

Biostatistics Faculty Publications

Historically, the majority of statistical association methods have been designed assuming availability of SNP-level information. However, modern genetic and sequencing data present new challenges to access and sharing of genotype-phenotype datasets, including cost of management, difficulties in consolidation of records across research groups, etc. These issues make methods based on SNP-level summary statistics particularly appealing. The most common form of combining statistics is a sum of SNP-level squared scores, possibly weighted, as in burden tests for rare variants. The overall significance of the resulting statistic is evaluated using its distribution under the null hypothesis. Here, we demonstrate that this basic …

Auspicious Symbols Of Rank And Status, Byron Breedlove, Isaac Fung

Biostatistics, Epidemiology & Environmental Health Sciences: Faculty Publications

Work published in Emerging Infectious Diseases.

Subsurface Analytics: Contribution Of Artificial Intelligence And Machine Learning To Reservoir Engineering, Reservoir Modeling, And Reservoir Management, Shahab D. Mohaghegh

Faculty & Staff Scholarship

Subsurface Analytics is a new technology that changes the way reservoir simulation and modeling is performed. Instead of starting with the construction of mathematical equations to model the physics of the fluid flow through porous media and then modification of the geological models in order to achieve history match, Subsurface Analytics that is a completely AI-based reservoir simulation and modeling technology takes a completely different approach. In AI-based reservoir modeling, field measurements form the foundation of the reservoir model. Using data-driven, pattern recognition technologies; the physics of the fluid flow through porous media is modeled through discovering the best, most …

Block Designs, Lucien Poulin, Daniela Genova

Showcase of Osprey Advancements in Research and Scholarship (SOARS)

Block designs are a type of combinatorial structures that can be used to model many different types of problems ranging from experimental design to computer software testing. They can be used to construct schemes that ensure complete optimization and efficiency of the given experiment. We focus mainly on Steiner and Kirkman triple systems, as well as, on different ways for constructing block designs. Well known results in combinatorics such as Fisher’s inequality and Kirkman’s schoolgirl problem are also discussed.

Insights From The Influx Of Prescription Painkillers In Northeast Florida: A Retrospective Analysis, Joseph Free, Michelle Dedeo

Showcase of Osprey Advancements in Research and Scholarship (SOARS)

The opioid epidemic has had, and will have, long-lasting ramifications in the United States. To better understand its impact in the Northeast Florida, this research seeks to identify relationships between hydro- and oxycodone pill concentration at the county and zip code levels and socio-economic factors such as average adjusted gross income and opioid related mortality. This project utilizes time series, regression, and GIS methods to examine local opioid saturation and has led to the development of an interactive Tableau dashboard which allows users to view opioid saturation at various levels of granularity. This analysis is made possible by longitudinal data …

The Expanded View Of Individualism And Collectivism: One, Two, Or Four Dimensions?, Jennifer L. Priestley, Kamal Fatehi, Gita Taasoobshirazi

Faculty Articles

Recent research to analyze and discuss cultural differences has employed a combination of five major dimensions of individualism–collectivism, power distance, uncertainty avoidance, femininity– masculinity (gender role differentiation), and long-term orientation. Among these dimensions, individualism–collectivism has received the most attention. Chronologically, this cultural attribute has been regarded as one, then two, and more recently, four dimensions of horizontal and vertical individualism and collectivism. However, research on this issue has not been conclusive and some have argued against this expansion. The current study attempts to explain and clarify this discussion by using a shortened version of the scale developed by Singelis et …

A Glossary On Building Longitudinal, Population-Based Data Linkages To Explore Children’S Developmental Trajectories, Jennifer E. V. Lloyd, Jacqui Boonstra, Lisa Chen, Barry Forer, Ruth Hershler, Constance Milbrath, Brenda T. Poon, Neda Razaz, Pippa Rowcliffe, Kimberly Schonert-Reichl

Journal of Modern Applied Statistical Methods

Population-based, person-specific, longitudinal child and youth health and developmental data linkages involve connecting combinations of specially-collected data and administrative data for longitudinal population research purposes. This glossary provides definitions of key terms and concepts related to their theoretical basis, research infrastructure, research methodology, statistical analysis, and knowledge translation.

Robust Confidence Intervals For The Population Mean Alternatives To The Student-T Confidence Interval, Moustafa Omar Ahmed Abu-Shawiesh, Aamir Saghir

Journal of Modern Applied Statistical Methods

In this paper, three robust confidence intervals are proposed as alternatives to the Student‑t confidence interval. The performance of these intervals was compared through a simulation study shows that Q_n-t confidence interval performs the best and it is as good as Student’s‑t confidence interval. Real-life data was used for illustration and performing a comparison that support the findings obtained from the simulation study.

Using Spss To Analyze Complex Survey Data: A Primer, Danjie Zou, Jennifer E. V. Lloyd, Jennifer L. Baumbusch

Journal of Modern Applied Statistical Methods

An introduction to using SPSS to analyze complex survey data is given. Key features of complex survey design are described briefly, including stratification, clustering, multiple stages, and weights. Then, annotated SPSS syntax for complex survey data analysis is presented to demonstrate the step-by-step process using real complex samples data.

Dynamic Control Of Probabilistic Simple Temporal Networks, James C. Boerkoel Jr., Michael Gao, Lindsay Popowski

All HMC Faculty Publications and Research

The controllability of a temporal network is defined as an agent’s ability to navigate around the uncertainty in its schedule and is well-studied for certain networks of temporal constraints. However, many interesting real-world problems can be better represented as Probabilistic Simple Temporal Networks (PSTNs) in which the uncertain durations are represented using potentially-unbounded probability density functions. This can make it inherently impossible to control for all eventualities. In this paper, we propose two new dynamic controllability algorithms that attempt to maximize the likelihood of successfully executing a schedule within a PSTN. The first approach, which we call MIN-LOSS DC, finds …

Limited Early Warnings And Public Attention To Coronavirus Disease 2019 In China, January–February, 2020: A Longitudinal Cohort Of Randomly Sampled Weibo Users, Yuner Zhu, King-Wa Fu, Karen A. Grépin, Hai Liang, Isaac Fung

Biostatistics, Epidemiology & Environmental Health Sciences: Faculty Publications

Objective:

Awareness and attentiveness have implications for the acceptance and adoption of disease prevention and control measures. Social media posts provide a record of the public’s attention to an outbreak. To measure the attention of Chinese netizens to coronavirus disease 2019 (COVID-19), a pre-established nationally representative cohort of Weibo users was searched for COVID-19-related key words in their posts.

Methods:

COVID-19-related posts (N = 1101) were retrieved from a longitudinal cohort of 52 268 randomly sampled Weibo accounts (December 31, 2019–February 12, 2020).

Results:

Attention to COVID-19 was limited prior to China openly acknowledging human-to-human transmission on …

Survival Mediation Analysis With The Death-Truncated Mediator: The Completeness Of The Survival Mediation Parameter, An-Shun Tai, Chun-An Tsai, Sheng-Hsuan Lin

Harvard University Biostatistics Working Paper Series

In medical research, the development of mediation analysis with a survival outcome has facilitated investigation into causal mechanisms. However, studies have not discussed the death-truncation problem for mediators, the problem being that conventional mediation parameters cannot be well-defined in the presence of a truncated mediator. In the present study, we systematically defined the completeness of causal effects to uncover the gap, in conventional causal definitions, between the survival and nonsurvival settings. We proposed three approaches to redefining the natural direct and indirect effects, which are generalized forms of the conventional causal effects for survival outcomes. Furthermore, we developed three statistical …

D-Vine Copula Model For Dependent Binary Data, Huihui Lin, N. Rao Chaganty

College of Sciences Posters

High-dimensional dependent binary data are prevalent in a wide range of scientific disciplines. A popular method for analyzing such data is the Multivariate Probit (MP) model. But the MP model sometimes fails even within a feasible range of binary correlations, because the underlying correlation matrix of the latent variables may not be positive definite. In this research, we proposed pair copula models, assuming the dependence between the binary variables is first order autoregressive (AR(1))or equicorrelated structure. Also, when Archimediean copula is used, most paper converted Kendall Tau to corresponding copula parameter, there is no explicit function of Pearson’s correlation coefficient …

On The Authentic Notion, Relevance, And Solution Of The Jeffreys-Lindley Paradox In The Zettabyte Era, Miodrag M. Lovric

Journal of Modern Applied Statistical Methods

The Jeffreys-Lindley paradox is the most quoted divergence between the frequentist and Bayesian approaches to statistical inference. It is embedded in the very foundations of statistics and divides frequentist and Bayesian inference in an irreconcilable way. This paradox is the Gordian Knot of statistical inference and Data Science in the Zettabyte Era. If statistical science is ready for revolution confronted by the challenges of massive data sets analysis, the first step is to finally solve this anomaly. For more than sixty years, the Jeffreys-Lindley paradox has been under active discussion and debate. Many solutions have been proposed, none entirely satisfactory. …