Statistics and Probability Commons^™

Mixture Modeling With Applications In Alzheimer's Disease, Frank Appiah

Theses and Dissertations--Epidemiology and Biostatistics

This dissertation involves an application of mixture of regression models to 114 individuals who are cognitively intact (from the Alzheimer's Disease and Neuroimaging Initiative-ADNI, data). The correct number of components in the model were estimated with the Singular BIC (SBIC), marking the first time it has been applied to such a problem. The smallest true model in conjunction with the approximation of SBIC was fixed at 1. The resulting posterior probabilities from the model were used to estimate the probability of a person transitioning and risk plots were obtained that could in principle be used by clinicians to identify patients …

Statistics-Bierce Library Study, Tyler J. Hushour

Williams Honors College, Honors Research Projects

This is a report from two surveys that I created and administered to students and faculty at Bierce library who came to the Circulation Desk or the Tech Desk, as well as some of my other findings when periodically looking around the library to see where students like to study or hang-out. There was a written survey given at the Circulation Desk, and a different survey given at the Tech Check-Out Desk. The project is for Melanie Smith-Farrell, the head of Access Services, and is based on a similar study Ian McCullough did in the science library. While this is …

Selection Portfolio: Applying Modern Portfolio Theory To Personnel Selection, Eric Leingang

All Graduate Theses, Dissertations, and Other Capstone Projects

Modern Portfolio Theory (MPT) is a framework for building a portfolio of risky assets such that the ratio of risk to return is minimized. While this theory has been used in the field of financial economics for over sixty years, the method has not yet been applied to compensatory personnel selection. A common method for personnel selection is multiple regression to maximize the predicted performance of the selected group given a cut-off score on the predictor(s). Recognizing that maximizing the performance of the selected group is not the only consideration, and that, for many jobs and organizations, the outcomes of …

Influences Of Probability Instruction On Undergraduates' Understanding Of Counting Processes, Kayla Blyman

Theses and Dissertations--Education Sciences

Historically, students in an introductory finite mathematics course at a major university in the mid-south have struggled the most with the counting and probability unit, leading instructors to question if there was a better way to help students master the material. The purpose of this study was to begin to understand connections that undergraduate finite mathematics students are making between counting and probability. By examining student performance in counting and probability, this study provides insights that inform future instruction in courses that include counting and probability. Consequently, this study lays the groundwork for future inquiries in the field of undergraduate …

A Functional Data Analytic Approach For Region Level Differential Dna Methylation Detection, Mohamed Salem F. Milad

Doctoral Dissertations

"DNA methylation is an epigenetic modification that can alter gene expression without a DNA sequence change. The role of DNA methylation in biological processes and human health is important to understand, with many studies identifying associations between specific methylation patterns and diseases such as cancer. In mammals, DNA methylation almost always occurs when a methyl group attaches to a cytosine followed by a guanine (i.e. CpG dinucleotides) on the DNA sequence. Many statistical methods have been developed to test for a difference in DNA methylation levels between groups (e.g. healthy vs disease) at individual cytosines. Site level testing is often …

Benefit Of Ultrasound Curriculum Development For Family Medicine Residents, Nithin Natwa, Uzair Munshey, Duncan Vos, Robert Baker

Research Day

Introduction/Purpose: Musculoskeletal problems comprise some of the most common reasons for ambulatory care encounters in the United States, accounting for 8.3% of the 1.2 billion visits per year according to the CDC. Musculoskeletal Ultrasound use has become more common in primary care for diagnosis and therapeutics. In Family Medicine Residency (FMR) Programs there is a deficiency of a structured, competency-based musculoskeletal ultrasound (MSK US) training despite its growing popularity. Currently, there is no formalized requirement for Ultrasound education as in other residency programs in spite of its benefit. Methods: We received a positive response on our needs analysis survey for …

Delivery Of Health Education In Adolescents With Behavioral Health Challenges, Ashley Akkal, Ransome Eke Md, Phd, Sulin Wu, Amy Rechenberg, Michael Madrid, Jose Lopez-Vera, Duncan Vos

Research Day

BACKGROUND Adolescents with behavioral health issues tend to have inadequate access to health education, and are thus less aware of the importance of personal and dental hygiene, exercise, and healthy diet and lifestyle habits. Due to this disparity, this population has been known to harbor a higher prevalence of STI’s, drug and alcohol abuse, physical altercations, juvenile detention, and suicide attempts. PURPOSE The overall objective of this study was to examine the effect of integrating a health science curriculum in this population. METHODS Participants aged 5-17 years old were recruited and assigned to either control or science groups by Family …

Determining Best Practices Of Peer Mediation Methods In Kalamazoo Public Schools, Melanie Bourgeau, Dagan Hammar, Neil Hughes, Sarah Kemp, Sydney Spitler, Cathy L. Kothari Phd

Research Day

Determining Best Practices of Peer Mediation methods in Kalamazoo Public Schools Melanie Bourgeau, Dagan Hammar, Neil Hughes, Sarah Kemp, Sydney Spitler, Catherine Kothari BACKGROUND Peer mediation is a method of conflict resolution in which a conflict between two people or groups is guided by a fellow student in order to reach an agreement. Peer mediation has been shown to be an effective tool in helping students resolve conflict and how to respond to future conflicts. This has led to a reduction in school violence and suspensions in schools that have adopted this method. Several methods have been employed in the …

Bounding And Stabilizing Realizations Of Biased Graphs With A Fixed Group, Nancy Ann Neudauer, Dan Slilaty

Mathematics and Statistics Faculty Publications

Given a group Γ and a biased graph (G, B), we define a what is meant by a Γ-realization of (G, B) and a notion of equivalence of Γ-realizations. We prove that for a finite group Γ and t ≥ 3, that there are numbers n(Γ) and n(Γ, t) such that the number of Γ-realizations of a vertically 3-connected biased graph is at most n(Γ) and that the number of Γ-realizations of a nonseparable biased graph without a (2Ct , ∅)-minor is at most n(Γ, t). Other results pertaining to contrabalanced biased graphs are presented as well as an analogue …

Chain Transitive Homeomorphisms On A Space: All Or None, Ethan Akin, Juho Rautio

Mathematics and Statistics Faculty Research & Creative Works

Extending earlier work, we consider when a compact metric space can be realized as the omega limit set of a discrete time dynamical system. This is equivalent to asking when the space admits a chain transitive homeomorphism. We approach this problem in terms of various conditions on the connected components of the space. We also construct spaces where all homeomorphisms are chain transitive.

A Markov Decision Process Approach To Adaptive Contact Strategies, Artur Grygorian

College of Graduate Studies: Theses & Dissertations

In the field of survey methodology, optimizing contact strategies helps organizations increase response rates using their allocated budget. Markov Decision Processes (MDP) are widely used to model decision-making strategies in situations where the outcomes have a random component. In this research, we use MDPs and adaptive sampling techniques to construct a strategy that, based on target audience characteristics, suggests the best contact policy. The data we use comes from the First Destination Survey conducted by the Office of Career Services at Georgia Southern University. The constructed model is quite flexible and can be used by other organizations to optimize their …

Neural Network Predictions Of A Simulation-Based Statistical And Graph Theoretic Study Of The Board Game Risk, Jacob Munson

Murray State Theses and Dissertations

We translate the RISK board into a graph which undergoes updates as the game advances. The dissection of the game into a network model in discrete time is a novel approach to examining RISK. A review of the existing statistical findings of skirmishes in RISK is provided. The graphical changes are accompanied by an examination of the statistical properties of RISK. The game is modeled as a discrete time dynamic network graph, with the various features of the game modeled as properties of the network at a given time. As the network is computationally intensive to implement, results are produced …

Identifying Predictors Of Weight Loss And Drop-Out Using Joint Modeling, Valerie Bares

Electronic Theses and Dissertations

Profile by Sanford is a membership based weight loss program that helps its members make lifestyle changes with diet, exercise, and one-on-one interactions with a weight loss coach. Discovery of characteristics and behaviors influencing weight loss will benefit current and future members of Profile. This research utilizes massive data from Profile by Sanford to analyze member behavior. Fourteen data sets are evaluated, some containing millions of observations. All data is combined into one comprehensive table of 33,487 members. Members of Profile by Sanford are 77% female and two-thirds of all members start the program classified as obese. Attending meetings with …

Threshold Models For Genome-Wide Association Mapping Of Familial Breast Cancer Incidence In Humans, Nasir Elmesmari

Electronic Theses and Dissertations

Breast cancer is the second most fatal cancer in the world and one of the most highly harmful cancers from which people suffer. Breast cancer studies have been able to uncover some knowledge about genetic susceptibility for familial breast cancer in humans. Hence, determining genetic factors may potentially help track the disease, as well as discover the cancer in early stages, or perhaps before it starts. In addition, this may allow early determination of possible treatment strategies which will make it easier to prevent the disease. In this context, it is important to determine whether the heritability of breast cancer …

Response Surface Methodology And Its Application In Optimizing The Efficiency Of Organic Solar Cells, Rajab Suliman

Electronic Theses and Dissertations

Response surface methodology (RSM) is a ubiquitous optimization approach used in a wide variety of scientific research studies. The philosophy behind a response surface method is to sequentially run relatively simple experiments or models in order to optimize a response variable of interest. In other words, we run a small number of experiments sequentially that can provide a large amount of information upon augmentation. In this dissertation, the RSM technique is utilized in order to find the optimum fabrication condition of a polymer solar cell that maximizes the cell efficiency. The optimal device performance was achieved using 10.25 mg/ml polymer …

Spatial And Spatiotemporal Modeling Of Epidemiological Data, Laxman Karki

Electronic Theses and Dissertations

This dissertation focuses on modeling approach for spatial and spatiotemporal data with epidemiological applications. Chapter one gives the general overview of spatial and spatiotemporal data and challenges in the statistical analysis of spatial and spatiotemporal data, and motivation and objectives of the study. Chapter two describes the regression models commonly used in spatial data analysis. Various types of regression methods such as OLS, GWR and MGWR were used to study the association between diabetes prevalence and socioeconomic and lifestyle factors on county level data of Midwestern United States. A new analysis workflow is purposed for regression analysis of spatial data. …

Development And Properties Of Kernel-Based Methods For The Interpretation And Presentation Of Forensic Evidence, Douglas Armstrong

Electronic Theses and Dissertations

The inference of the source of forensic evidence is related to model selection. Many forms of evidence can only be represented by complex, high-dimensional random vectors and cannot be assigned a likelihood structure. A common approach to circumvent this is to measure the similarity between pairs of objects composing the evidence. Such methods are ad-hoc and unstable approaches to the judicial inference process. While these methods address the dimensionality issue they also engender dependencies between scores when 2 scores have 1 object in common that are not taken into account in these models. The model developed in this research captures …

Juvenile Remains: Predicting Body Mass And Stature In Modern American Populations, Erin F E Pinkston

Cal Poly Humboldt theses and projects

There are increasing numbers of unidentified persons in the U.S. and abroad. To generate positive identifications, forensic anthropologists and others working in the medicolegal field employ a variety of methods to produce biological profiles to match to case files and missing persons databases. Body mass, and stature are two important components of a biological profile, and both can be estimated using regression formulae derived from skeletal metrics. In cases of unidentified juvenile remains, these are particularly important metrics, as it is difficult or impossible to determine sex in prepubescent remains, and the quality of ancestry estimation is currently under debate …

Approximate Bayesian Computation In Forensic Science, Jessie H. Hendricks

The Journal of Undergraduate Research

Forensic evidence is often an important factor in criminal investigations. Analyzing evidence in an objective way involves the use of statistics. However, many evidence types (i.e., glass fragments, fingerprints, shoe impressions) are very complex. This makes the use of statistical methods, such as model selection in Bayesian inference, extremely difficult.

Approximate Bayesian Computation is an algorithmic method in Bayesian analysis that can be used for model selection. It is especially useful because it can be used to assign a Bayes Factor without the need to directly evaluate the exact likelihood function - a difficult task for complex data. Several criticisms …

Approximate Statistical Solutions To The Forensic Identification Of Source Problem, Danica M. Ommen

Electronic Theses and Dissertations

Currently in forensic science, the statistical methods for solving the identification of source problems are inherently subjective and generally ad-hoc. The formal Bayesian decision framework provides the most statistically rigorous foundation for these problems to date. However, computing a solution under this framework, which relies on a Bayes Factor, tends to be computationally intensive and highly sensitive to the subjective choice of prior distributions for the parameters. Therefore, this dissertation aims to develop statistical solutions to the forensic identification of source problems which are less subjective, but which retain the statistical rigor of the Bayesian solution. First, this dissertation focuses …

U-Statistics For Characterizing Forensic Sufficiency Studies, Cami Fuglsby

Electronic Theses and Dissertations

One of the main metrics for deciding if a given forensic modality is useful across a broad spectrum of cases, within a given population, is the Random Match Probability (RMP), or the corresponding discriminating power. Traditionally, the RMP of a given modality is studied by comparing full `templates' and estimating the rate at which pairs of templates 'match' in a given population. This strategy leads to a natural U-statistic of degree two. However, in questioned document examination, the RMP is studied as a function of the amount of handwriting contained in the two documents being compared; turning the U-statistic into …

A Kernel Based Approach To Determine Atypicality, Austin O'Brien

Electronic Theses and Dissertations

This dissertation outlines the development and use for a new probabilistic measure for categorization, referred to as atypicality. Given a set of known source objects, we can create a corresponding set of similarity scores between them. Assuming the set of scores has a normal distribution, we can estimate its parameters. Then, we can introduce new trace objects to the problem, and compute similarity scores for them. The main goal of the atypicality score is to determine if the new trace objects are similar to the source objects. To do this, we bootstrap many new scores using the estimated parameters (from …

Comparative Study Of The Distribution Of Repetitive Dna In Model Organisms, Mohamed K. Aburweis

Electronic Theses and Dissertations

Repetitive DNA elements are abundant in the genome of a wide range of organisms. In mammals, repetitive elements comprise about 40-50% of the total genomes. However, their biological functions remain largely unknown. Analysis of their abundance and distribution may shed some light on how they affect genome structure, function, and evolution. We conducted a detailed comparative analysis of repetitive DNA elements across ten different eukaryotic organisms, including chicken (G. gallus), zebrafish (D. rerio), Fugu (T. rubripes), fruit fly (D. melanogaster), and nematode worm (C. elegans), along with five mammalian organisms: human (H. sapiens), mouse (M. musculus), cow (B. taurus), rat …

Development Of Computational Techniques For Regulatory Dna Motif Identification Based On Big Biological Data, Jinyu Yang

Electronic Theses and Dissertations

Accurate regulatory DNA motif (or motif) identification plays a fundamental role in the elucidation of transcriptional regulatory mechanisms in a cell and can strongly support the regulatory network construction for both prokaryotic and eukaryotic organisms. Next-generation sequencing techniques generate a huge amount of biological data for motif identification. Specifically, Chromatin Immunoprecipitation followed by high throughput DNA sequencing (ChIP-seq) enables researchers to identify motifs on a genome scale. Recently, technological improvements have allowed for DNA structural information to be obtained in a high-throughput manner, which can provide four DNA shape features. The DNA shape has been found as a complementary factor …

Bayesian Exponential Random Graph Modelling Of Interhospital Patient Referral Networks, Alberto Caimo, Francesca Pallotti, Alessandro Lomi

Articles

Using original data that we have collected on referral relations between 110 hospitals serving a large regional community, we show how recently derived Bayesian exponential random graph models may be adopted to illuminate core empirical issues in research on relational coordination among healthcare organisations. We show how a rigorous Bayesian computation approach supports a fully probabilistic analytical framework that alleviates well-known problems in the estimation of model parameters of exponential random graph models. We also show how the main structural features of interhospital patient referral networks that prior studies have described can be reproduced with accuracy by specifying the system …

Cutaneous Malignant Melanoma Incidences Analyzed Worldwide By Skin Type Over Advancing Age Of Males And Females: Evidence Estrogen And Androgenic Hair Are Risk Factors, Dianne E. Godar, Madhan Subramanian, Stephen Merrill

Mathematics, Statistics and Computer Science Faculty Research and Publications

We previously analyzed cutaneous malignant melanoma (CMM) incidences worldwide by sex, age, and Fitzpatrick skin type over time (1955-2007) and found only European-ancestry populations have exponential increasing incidences and about a 2-log increase in the risk between the youngest age groups (0-14 and 15-29 yr). We proposed the increasing incidence over time may be from the spread of Human Papilloma Virus (HPV) found in CMM biopsies, and that the 2-log incidence increase between the youngest age groups might be from developing androgenic hair. The increasing incidence with age may be from white hairs transmitting UV radiation to follicular melanocytes. Here …

Statistical Study For Bridge Deterioration Across Alabama, Cameron Mcwilliams

Summer Community of Scholars Posters (RCEU and HCR Combined Programs)

No abstract provided.

Association Between Hiv And Violence Among Female Commercial Sex Workers In Ukraine : Analysis Of Bio-Behavioral Surveillance Conducted In 2015-2016, Ganna Momotyuk

Legacy Theses & Dissertations (2009 - 2024)

A cross-sectional analysis investigated the association between HIV and violence in female commercial sex workers (FCSW) in Ukraine between 10/2015 and 01/2016. Methods: 3,885 FCSW from a total of 4,300 were questioned about behavioral and social demographics and tested for HIV in mobile testing van. Results: of the 3,885 respondents, 5.89% were HIV positive, and 47.00% had experienced violence. We tested for and found that drug use was an effect modifier for the association between HIV and violence. Analyses were stratified by injecting drug use and no injecting drug use. High risk for HIV was found in the non-IDU stratum …

Raman Spectroscopy And Chemometrics For Forensic Bloodstain Analysis : Species Differentiation, Donor Age Estimation, And Dating Of Bloodstains, Kyle C. Doty

Legacy Theses & Dissertations (2009 - 2024)

The field of forensic science is constantly growing, so the advancement of old and unreliable techniques is at the forefront of what will lead to future progress and improvement. Current methods for identification and analysis of bloodstains are underwhelming due to the insignificant amount of information provided in a destructive, unreliable, and unsafe manner. As is the purpose of this research, creating new methodologies that are rapid, nondestructive, robust, statistically reliable, and safe would significantly advance the way bloodstains are currently analyzed, while providing more useful and relevant information for investigations and criminal proceedings. Raman spectroscopy, along with advanced statistical …

Computationally Efficient Multiple Imputation Routines In Clustered Data, Tugba Akkaya-Hocagil

Legacy Theses & Dissertations (2009 - 2024)

Presence of missing data in correlated data settings is a non-trivial problem. Inference by multiple imputation offers a viable solution to analysts. However, the missing data problem is typically more complicated due to diverse measurement scales, skip patterns, bounds and restrictions. Sequential regression imputation also known as variable-by-variable imputation has emerged as a popular imputation modeling technique, especially in the complex data structures. In this dissertation, we develop three methods to handle incomplete data in hierarchically nested and non-nested multilevel data structures using sequential regression imputation approach.