Statistics and Probability Commons^™

Differential Privacy For Regression Modeling In Health: An Evaluation Of Algorithms, Joseph Ficek

USF Tampa Graduate Theses and Dissertations

Background: There is a need for rigorous and standardized methods of privacy protection for shared data in the health sciences. Differential privacy is one such method that has gained much popularity due to its versatility and robustness. This study evaluates differential privacy for explanatory regression modeling in the context of health research.

Methods: Surveyed and newly proposed algorithms were evaluated with respect to the accuracy (bias and RMSE) of coefficient estimates, the empirical coverage probability of confidence intervals, and the power and type I error rates of hypothesis tests. Evaluations took place in both simulated and real data from a …

Online And Adjusted Human Activities Recognition With Statistical Learning, Yanjia Zhang

USF Tampa Graduate Theses and Dissertations

Wearable human activity recognition (HAR) is a widely application system for our daily life. It hasbeen built in many devices, such as smartphone, smartwatch, activity tracker, and health monitor. Many researchers try to develop a system which requires less memory space and power, but has fast and accurate classification results. Moreover, the objective of adjusting the classifier by the system self is also a study direction. In the present study, we introduced the machine learning methods to both smartphone data and smartwatch data and an adjusted model with the continuous generating data. Further, we also proposed a new HAR system …

Development And Validation Of A Scale To Measure Songwriting Self-Efficacy (Sses) With Secondary Music Students, Patrick K. Cooper

USF Tampa Graduate Theses and Dissertations

Social cognitive theory was developed to explain how individuals learn, in part, by witnessing the behavior of others. Self-efficacy is a construct within social cognitive theory which indicates the beliefs that an individual can be successful at a task under specific situational demands. The sources of self-efficacy include self-evaluating past experiences to predict future success, comparing our abilities to those around us, the verbal and social feedback we get from others, and the physiological feelings we experience when engaged in or thinking about the task. Measures of self-efficacy have been shown to be accurate predictors of successful learning outcomes, achievement, …

Bayesian Multivariate Joint Modeling For Skewed-Longitudinal And Time-To-Event Data, Lan Xu

USF Tampa Graduate Theses and Dissertations

In epidemiologic and clinical studies, a relatively large number of biomarkers are repeatedly measured in patients over time, often associated with data on epidemiologic and clinical interest events. So, much attention is focused on developing the specific patterns of the longitudinal measurements, and the associations between those patterns and the time to a certain event, such as heart attack, diagnose of disease, time to transplantation, or death. In the last two decades, the research into joint modeling of longitudinal and time-to-event data has received a tremendous amount of attention.

Numerous researchers have proposed joint modeling approaches for a single longitudinal …

Data-Driven Analytical Modeling Of Multiple Myeloma Cancer, U.S. Crop Production And Monitoring Process, Lohuwa Mamudu

USF Tampa Graduate Theses and Dissertations

Globally, cancer disease is a major health issue causing a lot of deaths. The duration of time an individual diagnosed with a particular type of cancer survives has become a major area of research concern. The Kaplan Meier and Cox Proportional Hazard (Cox-PH) model have been a traditionally used method for survival analysis of cancer data. These techniques of cancer survival analysis are developed from nonparametric and semi-parametric approaches, respectively, which are not as robust as a parametric approach. In this dissertation, we proposed a new method of cancer survival analysis based on a parametric approach using multiple myeloma cancer …

Combination Of Time Series Analysis And Sentiment Analysis For Stock Market Forecasting, Hsiao-Chuan Chou

USF Tampa Graduate Theses and Dissertations

The goal of this research is to build a model to predict trend of financial asset price using sentiment from news headlines and financial indicators of the asset. Objective of the model is to conclude good results but also to minimize the difference between predicted values and actual values. Unlike previous approaches where the sentiments are usually calculated into score, we focus on combination of word embedding of news and financial indicators due to nonavailability of sentiment lexicon.

One idea is that the sentiment of news headline should have impact on financial asset val- ues. In other words, it would …

The General Psychopathology Factor (P) From Adolescence To Adulthood: Disentangling The Developmental Trajectories Of P Using A Multi-Method Approach, Alexandria M. Choate

USF Tampa Graduate Theses and Dissertations

Considerable attention is directed towards studying co-occurring psychopathology through the lens of a general factor (p-factor). However, the developmental trajectories and stability of the p-factor have yet to be fully understood. Study 1 first examined the explanatory power of dynamic mutualism theory — an alternative framework positing the p-factor to be a product of lower-level symptom interactions rather than the inherent cause of them. Predictions of dynamic mutualism were tested using three distinct statistical approaches including: longitudinal bifactor models, random-intercept cross-lagged panel models (RI-CLPMs), and network models. Next, given prior suggestions that borderline personality disorder (BPD) could be a marker …

Multimodal Data Fusion And Attack Detection In Recommender Systems, Mehmet Aktukmak

USF Tampa Graduate Theses and Dissertations

The commercial platforms that use recommender systems can collect relevant information to produce useful recommendations to the platform users. However, these sources usually contain missing values, imbalanced and heterogeneous data, and noisy observations. Such characteristics render the process of exploiting the information nontrivial, as one should carefully address them during the data fusion process. In addition to the degenerative characteristics, some entries can be fake, i.e., they can be the outcomes of malicious intents to manipulate the system. These entries should be eliminated before incorporation to any recommendation task. Detecting such malicious attacks quickly and accurately and then mitigating them …

Numerical Study Of Gap Distributions In Determinantal Point Process On Low Dimensional Spheres: L-Ensemble Of O(N) Model Type For N = 2 And N = 3, Xiankui Yang

USF Tampa Graduate Theses and Dissertations

Poisson point process is the most well-known point process with many applications. Unlike Poisson point process, which is the random set of non-intersecting points, determinantal point process refers to certain class of point processes where the points tend to interact with each other. The interaction often leads to more uniformly distributed points compared to those in Poisson point process.

In this article, we study the gap distribution of certain class of determinantal point process, L-ensemble of O(n) model type, and compare the distribution with the ones from the other known determinantal point process that appears in random matrices. Our numerical …

Bayesian Reliability Analysis For Optical Media Using Accelerated Degradation Test Data, Kun Bu

USF Tampa Graduate Theses and Dissertations

ISO (the International Organization for Standardization) 10995:2011 is the inter-national standard providing guidelines for assessing the reliability and service life of optical media, which is designed to be highly reliable and possesses a long lifetime. A well-known challenge of reliability analysis for highly reliable devices is that it is hard to obtain sufficient failure data under their normal use conditions. Accelerated degradation tests (ADTs) are commonly used to quickly obtain physical degradation data under elevated stress conditions, which are then extrapolated to predict reliability under the normal use condition. This standard achieves the estimation of the lifetime of recordable media, …

Identification Of Patterns And Disruptions In Ambient Sensor Data From Private Homes, Yan Wang

USF Tampa Graduate Theses and Dissertations

The world’s population is rapidly aging and the increasing demand for home and health care services from this aging population brings unprecedented challenges to the economy and society. Ambient-assisted smart homes, residences equipped with ambient sensors to monitor the resident’s daily activities in a continuous and unobtrusive way, present great potential to manage the growing care service needs of this older population segment, and enable them to age-in-place.

Despite growing research, using ambient sensor data from private homes to monitor daily activities, health and wellness still faces significant challenges. To study ambient sensor data from private homes where annotated data …

Predictive Validity Of Standards-Based And Curriculum-Embedded Assessments For Predicting Readiness At Kindergarten Entry, Elizabeth Ashton Decamilla

USF Tampa Graduate Theses and Dissertations

As with traditional K-12 educational settings, early childhood assessments have been a primary source of information determining whether early educational experiences have promoted children’s readiness to start school in kindergarten. The level of use of Kindergarten Entry Assessments (KEAs) has become more wide-spread to establish levels of school readiness at kindergarten entry.

This quantitative, correlational study of children in schools that have blended Head Start/Voluntary Prekindergarten funded programs examined the predictive relationships between the independent variables (i.e., VPK Assessments and Teaching Strategies GOLD) and the dependent variable of kindergarten readiness, as measured by the Work Sampling System™ (WSS). Additionally, the …

Exploration Of Factors Associated With Perceptions Of Community Safety Among Youth In Hillsborough County, Florida: A Convergent Parallel Mixed-Methods Approach, Yingwei Yang

USF Tampa Graduate Theses and Dissertations

Introduction: Youth perceived safety is not only linked to crime and violence in a neighborhood but is also associated with health risk behaviors and certain neighborhood characteristics. The purpose of this mixed-methods study was to measure the co-occurring effects of individual and community risk factors by conducting a secondary data analysis using structural equation modeling (SEM) and to explore reasons for youth feeling safe/unsafe in their community using photovoice methodology.

Methods: Syndemic theory/model served as the theoretical framework to guide this mixed-methods study with a convergent parallel design. The quantitative strand (first manuscript) utilized an existing dataset collected from middle …

Bayesian Reliability Analysis Of The Power Law Process And Statistical Modeling Of Computer And Network Vulnerabilities With Cybersecurity Application, Freeh N. Alenezi

USF Tampa Graduate Theses and Dissertations

As most of mankind now lives in an era of high dependence on multiple technologies and complex systems to store and manage sensitive information, researchers are constantly urged to obtain and improve measurements and methodologies that have the ability to evaluate systems reliability and security. The objectives of the present dissertation are to improve the Bayesian reliability estimation of a software package where the Power Law Process, also known as Non-Homogeneous Poisson Process, is the underlying failure model and to develop a set of statistical models evaluating computer operating systems vulnerabilities. Furthermore, we develop a reliability function of a computer …

Gradient Boosting For Survival Analysis With Applications In Oncology, Nam Phuong Nguyen

USF Tampa Graduate Theses and Dissertations

Cancer is one of the most deadly diseases that the world has been fighting against over decades. An enormous number of research has been conducted, via a wide scale of approaches, raging from genetic analysis to mathematical modeling. Survival analysis is a well-performed methodology frequently used to estimate the survival probability of a patient. Although there has been a large number of methods for survival analysis, efficient exploration of a high-dimensional feature space has been challenging due to its computational cost and complexity. This thesis adapts the component-wise gradient boosting algorithms for cancer survival analysis, and also proposes a new …

Fractional Random Weighted Bootstrapping For Classification On Imbalanced Data With Ensemble Decision Tree Methods, Sean Charles Carter

USF Tampa Graduate Theses and Dissertations

Ensemble methods are commonly used for building predictive models for classification. Models that are unstable to perturbations in the training set, such as the decision tree, often see considerable reductions in error when grouped, using bootstrapped resamples of the training data to train many models. The non-parametric bootstrap, however, has limited efficacy when used on severely imbalanced data, especially when the number of observations of one or more classes is exceptionally small. We explore the fractional random weighted bootstrap, which randomly assigns fractional weights to observations, as an alternative resampling pro cedure in training machine learning ensembles, particularly decision tree …

Probabilistic Modeling Of Democracy, Corruption, Hemophilia A And Prediabetes Data, A. K. M. Raquibul Bashar

USF Tampa Graduate Theses and Dissertations

Parametric analysis of any real-world data is the most powerful tool to characterize the probabilistic behavior in social, economic, medical, epidemiological, and other areas of study. In the present study, we identify the theoretical Probability Distribution Function(PDF) for Democracy Index Scores (DIS) from the Economist Intelligence Unit (EIU) database and estimate the maximum likelihood estimates of the theoretical PDFS. We also identify the individual PDFs for each of the clusters, Full Democracy, Flawed Democracy, Hybrid Regime, and Authoritarian Regime defined by the Economist Intelligence Unit (EIU).

A statistical model is a convenient instrument to predict the future value of any …

Statistical Learning Of Biomedical Non-Stationary Signals And Quality Of Life Modeling, Mahdi Goudarzi

USF Tampa Graduate Theses and Dissertations

Statistical learning is a set of tools for modeling and understanding complex datasets. It is a recently developed area in statistics and blends with parallel developments in computer science and, in particular, machine learning.

The classification of biomedical non-stationary signals such as Electroencephalogram (EEG) is always a challenging problem due to their complexity. The low spatial resolution on the scalp, curse of dimensionality, poor signal-to-noise ratio are disadvantages of working with biomedical signals. EEG signals are unstructured data which needs preprocessing steps to extract informative features which are measurable and predictive. In the first two chapters of this dissertation, EEG …

Probabilistic And Statistical Prediction Models For Alzheimer’S Disease And Statistical Analysis Of Global Warming, Maryam Ibrahim Habadi

USF Tampa Graduate Theses and Dissertations

The importance and applicability of data-driven statistical models have increased significantly. This current study, we have utilized statistical techniques in interdisciplinary research, including environmental and health.

Environmentally, global warming is considered one of the critical issues facing our planet. It is the increase in average global temperatures caused mostly by increases in Carbon Dioxide CO₂. The excessive rise of carbon dioxide from the average level as the side effect of the industrial revolution has a significant impact on blocking the heat and increase the temperature within the Earth’s atmosphere. Based on the record of total CO₂ emissions …

Essays On Time Series And Machine Learning Techniques For Risk Management, Michael Kotarinos

USF Tampa Graduate Theses and Dissertations

The Capital Asset Pricing Model combined with the Sharpe ratio is a standard method for choosing assets for selection in a portfolio. However, this method has many structural issues and was designed for a time when high dimensional computing was in its infancy. An alternative to these methods using a mix of Multi-Level Time Series Clustering, the MACBETH algorithm and traditional time series techniques was constructed that minimized data loss and allow for customized portfolio construction for investors with different risk profiles and specialized investment needs. It was shown that these methods are adaptable to cloud computing environments and allow …

Exploring The Behavior Of Model Fit Criteria In The Bayesian Approximate Measurement Invariance: A Simulation Study, Abeer Atallah S. Alamri

USF Tampa Graduate Theses and Dissertations

Measurement invariance (MI) is conducted to ensure that differences found in the results of group comparisons are due to true substantive differences and not methodological artifacts. Previous cross-cultural and cross-national studies with large number of groups showed that the advanced measurement invariance level was rarely held when utilizing the traditional (frequentist) MI approach. The Bayesian approximate measurement invariance (BAMI) was introduced to override the traditional MI strict assumption, because trivial non-invariance in parameters across groups is allowed. Although the concept of the BAMI, which has been utilized since 2013, was incorporated into the context of structural equation modeling, there is …

Flowgraph Models For Clustered Multistate Time To Event Data, Kristin Hall

USF Tampa Graduate Theses and Dissertations

Healthcare systems have multistate processes. Such processes may be modeled using flowgraphs, which are directed graphs. Flowgraph models support a variety of transition time distributions, easily handle reversibility between states and allow alternate paths to the event or state of interest to be taken. However, estimation of flowgraph and first passage time distribution parameters can lead to incorrect inferences when interdependent data are treated as independent.

In this dissertation, we expand the flowgraph model to accommodate nested and correlated data structures. We develop a framework to incorporate random effects into transition probability and transition time components of a flowgraph model. …

Human Activity Recognition Based On Transfer Learning, Jinyong Pang

USF Tampa Graduate Theses and Dissertations

Human activity recognition (HAR) based on time series data is the problem of classifying various patterns. Its widely applications in health care owns huge commercial benefit. With the increasing spread of smart devices, people have strong desires of customizing services or product adaptive to their features. Deep learning models could handle HAR tasks with a satisfied result. However, training a deep learning model has to consume lots of time and computation resource. Consequently, developing a HAR system effectively becomes a challenging task. In this study, we develop a solid HAR system using Convolutional Neural Network based on transfer learning, which …

Application Of The Fusion Model For Cognitive Diagnostic Assessment With Non-Diagnostic Algebra-Geometry Readiness Test Data, Robert H. Fay

USF Tampa Graduate Theses and Dissertations

This study retrofitted a Diagnostic Classification Model (DCM) known as the Fusion model onto non-diagnostic test data from of the University of Chicago School Mathematics Project (UCSMP) Algebra and Geometry Readiness test post-test used with Transition Mathematics (Third Edition, Field-Trial Version). The test contained 24 multiple-choice middle school math items, and was originally given to 95 advanced 6th grade and 293 7th grade students. The use of these test answers for this study was an attempt to show that by using cognitive diagnostic analysis techniques on test items not constructed for that purpose, highly predictable multidimensional cognitive attribute profiles for …

Machine Learning Methods For Network Intrusion Detection And Intrusion Prevention Systems, Zheni Svetoslavova Stefanova

USF Tampa Graduate Theses and Dissertations

Given the continuing advancement of networking applications and our increased dependence upon software-based systems, there is a pressing need to develop improved security techniques for defending modern information technology (IT) systems from malicious cyber-attacks. Indeed, anyone can be impacted by such activities, including individuals, corporations, and governments. Furthermore, the sustained expansion of the network user base and its associated set of applications is also introducing additional vulnerabilities which can lead to criminal breaches and loss of critical data. As a result, the broader cybersecurity problem area has emerged as a significant concern, with many solution strategies being proposed for both …

Statistical Analysis And Modeling Of Cyber Security And Health Sciences, Nawa Raj Pokhrel

USF Tampa Graduate Theses and Dissertations

Being in the era of information technology, importance and applicability of analytical statistical model an interdisciplinary setting in the modern statistics have increased significantly. Conceptually understanding the vulnerabilities in statistical perspective helps to develop the set of modern statistical models and bridges the gap between cybersecurity and abstract statistical /mathematical knowledge. In this dissertation, our primary goal is to develop series of the strong statistical model in software vulnerability in conjunction with Common Vulnerability Scoring System (CVSS) framework. In nutshell, the overall research lies at the intersection of statistical modeling, cybersecurity, and data mining. Furthermore, we generalize the model of …

Signal Detection Of Adverse Drug Reaction Using The Adverse Event Reporting System: Literature Review And Novel Methods, Minh H. Pham

USF Tampa Graduate Theses and Dissertations

One of the objectives of the U.S. Food and Drug Administration is to protect the public health through post-marketing drug safety surveillance, also known as Pharmacovigilance. An inexpensive and efficient method to inspect post-marketing drug safety is to use data mining algorithms on electronic health records to discover associations between drugs and adverse events.

The purpose of this study is two-fold. First, we review the methods and algorithms proposed in the literature for identifying association drug interactions to an adverse event and discuss their advantages and drawbacks. Second, we attempt to adapt some novel methods that have been used in …

Optimal Latin Hypercube Designs For Computer Experiments Based On Multiple Objectives, Ruizhe Hou

USF Tampa Graduate Theses and Dissertations

Latin hypercube designs (LHDs) have broad applications in constructing computer experiments and sampling for Monte-Carlo integration due to its nice property of having projections evenly distributed on the univariate distribution of each input variable. The LHDs have been combined with some commonly used computer experimental design criteria to achieve enhanced design performance. For example, the Maximin-LHDs were developed to improve its space-filling property in the full dimension of all input variables. The MaxPro-LHDs were proposed in recent years to obtain nicer projections in any subspace of input variables. This thesis integrates both space-filling and projection characteristics for LHDs and develops …

Angiostrongylus Cantonensis: Epidemiologic Review, Location-Specific Habitat Modelling, And Surveillance In Hillsborough County, Florida, U.S.A., Brad Christian Perich

USF Tampa Graduate Theses and Dissertations

Angiostrongylus cantonensis is a parasitic nematode endemic to tropical and subtropical regions and is the leading cause of human eosinophilic meningitis. The parasite is commonly known as rat lungworm because the primary host in its lifecycle is the rat. A clinical overview of rat lungworm infection is presented, followed by a literature review of rat lungworm epidemiology, risk factors, and surveillance projects. Data collected from previous snail surveys in Florida was considered alongside elevation, population per square kilometer, median household income by zip code territory, and normalized difference vegetation index specific to the geographic coordinates from which the snail samples …

Strategies To Adjust For Response Bias In Clinical Trials: A Simulation Study, Victoria R. Swaidan

USF Tampa Graduate Theses and Dissertations

Background: Response bias can distort treatment effect estimates and inferences in clinical trials. Although prevention, quantification, and adjustments have been developed, current methods are not applicable when subject-level reliability is used as the measure of response bias. Thus, the objective of the current study is to develop, test, and recommend a series of bias correction strategies for use in these cases. Methods: Monte Carlo simulation and logistic regression modeling were used to develop the strategies, examining the collective impact of sample size (N), effect size (ES), reliability distribution, and response style on estimating the treatment effect size in a series …