Physical Sciences and Mathematics Commons^™

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 …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

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. …