Applied Statistics Commons^™

The Use Of Item Response Theory In Survey Methodology: Application In Seat Belt Data, Mark K. Ledbetter, Norou Diawara, Bryan E. Porter

Mathematics & Statistics Faculty Publications

Problem: Several approaches to analyze survey data have been proposed in the literature. One method that is not popular in survey research methodology is the use of item response theory (IRT). Since accurate methods to make prediction behaviors are based upon observed data, the design model must overcome computation challenges, but also consideration towards calibration and proficiency estimation. The IRT model deems to be offered those latter options. We review that model and apply it to an observational survey data. We then compare the findings with the more popular weighted logistic regression. Method: Apply IRT model to the observed data …

Car Insurance Rate-Making With An Eye Toward The Future, Stephen Howard

Williams Honors College, Honors Research Projects

For my project, I investigated car insurance rate-making. I took an in-depth look at the car insurance industry. I also studied driverless cars, and the expected timeline surrounding them. I also took a look at how driverless cars are expected to change the car insurance industry in the coming decades. In general, what I found did not surprise me. I did, however, glean insight from various opinions that I read about how the insurance industry is likely to change. Change of some sort in the car insurance industry is sure to come, with companies likely to become much more multi-faceted. …

Campus Climate Sexual Assault Survey (2015) Analysis, Felicia Rosin

Williams Honors College, Honors Research Projects

The issue of sexual assault has garnered widespread attention in recent years, as is evident by the growing number of high-profile cases and mainstream social movements. With this increasingly bright spotlight, it is no surprise that The University of Akron has interest in improving the sexual violence education programs offered to students. In 2015, the university conducted a survey to gather information on the campus climate surrounding sexual assault. This analysis dives into a deeper analysis of the data gathered in an attempt to pinpoint areas that require the university’s attention. The analysis covers topics identified by Dean of Students …

A Review Of The Utility Of Bayesian Network Models, Luke Magyar

Williams Honors College, Honors Research Projects

Bayesian Networks are probabilistic models built from conditional probability tables that relate two observable instances to one another in parent-child fashion. The networks’ strength lies in their ability to use inferential logic to make likelihood assessments about a parent node based on an observation of its child. Additionally, they make it very easy to combine quantitative data with qualitative knowledge from industry experts. These abilities make them very attractive for use as formulation tools in the paint and rubber industries. Paint and rubber formulation has long proven to be a challenging task because companies have a difficult time compiling the …

Decision Trees: Predicting Future Losses For Insurance Data, Amanda Lahrmann

Williams Honors College, Honors Research Projects

Big data is a term that has come to the spotlight for companies within recent years. Data analysis and business intelligence have become prominent sectors of companies and agencies. But what is big data? How has it impacted large companies and agencies? Why must it be embraced?

The best way to approach utilizing a big data set is to establish a question to answer. For this data set, the question that must be answered is “What variables cause a loss to occur?” To answer this question, first, we must understand what is meant by a “loss”, and take a look …

Penalized Mixed-Effects Ordinal Response Models For High-Dimensional Genomic Data In Twins And Families, Amanda E. Gentry

Theses and Dissertations

The Brisbane Longitudinal Twin Study (BLTS) was being conducted in Australia and was funded by the US National Institute on Drug Abuse (NIDA). Adolescent twins were sampled as a part of this study and surveyed about their substance use as part of the Pathways to Cannabis Use, Abuse and Dependence project. The methods developed in this dissertation were designed for the purpose of analyzing a subset of the Pathways data that includes demographics, cannabis use metrics, personality measures, and imputed genotypes (SNPs) for 493 complete twin pairs (986 subjects.) The primary goal was to determine what combination of SNPs and …

Joint Analysis Of Multiple Phenotypes In Association Studies, Xiaoyu Liang

Dissertations, Master's Theses and Master's Reports

Genome-wide association studies (GWAS) have become a very effective research tool to identify genetic variants of underlying various complex diseases. In spite of the success of GWAS in identifying thousands of reproducible associations between genetic variants and complex disease, in general, the association between genetic variants and a single phenotype is usually weak. It is increasingly recognized that joint analysis of multiple phenotypes can be potentially more powerful than the univariate analysis, and can shed new light on underlying biological mechanisms of complex diseases. Therefore, developing statistical methods to test for genetic association with multiple phenotypes has become increasingly important. …

Step-Selection Functions For Modeling Animal Movement -- Case Study: African Buffalo, Maia Adar

CMC Senior Theses

Understanding what factors influence wildlife movement allows landscape planners to make informed decisions that benefit both animals and humans. New quantitative methods, such as step-selection functions, provide valuable objective analyses of wildlife connectivity. This paper provides a framework for creating a step-selection function and demonstrates its use in a case study. The first section provides a general introduction about wildlife connectivity research. The second section explains the math behind the step-selection function using a simple example. The last section gives the results of a step-selection model for African buffalo in the Kavango Zambezi Transfrontier Conservation Area. Buffalo were found to …

Some New And Generalized Distributions Via Exponentiation, Gamma And Marshall-Olkin Generators With Applications, Hameed Abiodun Jimoh

College of Graduate Studies: Theses & Dissertations

Three new generalized distributions developed via completing risk, gamma generator, Marshall-Olkin generator and exponentiation techniques are proposed and studied. Structural properties including quantile functions, hazard rate functions, moment, conditional moments, mean deviations, R\'enyi entropy, distribution of order statistics and maximum likelihood estimates are presented. Monte Carlo simulation is employed to examine the performance of the proposed distributions. Applications of the generalized distributions to real lifetime data are presented to illustrate the usefulness of the models.

Wildfire Emissions In The Context Of Global Change And The Implications For Mercury Pollution, Aditya Kumar

Dissertations, Master's Theses and Master's Reports

Wildfires are episodic disturbances that exert a significant influence on the Earth system. They emit substantial amounts of atmospheric pollutants, which can impact atmospheric chemistry/composition and the Earth’s climate at the global and regional scales. This work presents a collection of studies aimed at better estimating wildfire emissions of atmospheric pollutants, quantifying their impacts on remote ecosystems and determining the implications of 2000s-2050s global environmental change (land use/land cover, climate) for wildfire emissions following the Intergovernmental Panel on Climate Change (IPCC) A1B socioeconomic scenario.

A global fire emissions model is developed to compile global wildfire emission inventories for major atmospheric …

A Land Use Regression Model For Explaining Spatial Variation In Air Pollution Levels Using A Wind Sector Based Approach, Owen Naughton, Aoife Donnelly, Paul Nolan, Francesco Pilla, Bruce Misstear, Brian Broderick

Articles

Estimating pollutant concentrations at a local and regional scale is essential for good ambient air quality information in environmental and health policy decision making. Here we present a land use regression (LUR) modelling methodology that exploits the high temporal resolution of fixed-site monitoring (FSM) to produce viable air quality maps. The methodology partitions concentration time series from a national FSM network into wind-dependent sectors or “wedges”. A LUR model is derived using predictor variables calculated within the directional wind sectors, and compared against the long-term average concentrations within each sector. This study demonstrates the value of incorporating the relative position …

Long-Term Outcomes After Elective Sterilization Procedures — A Comparative Retrospective Cohort Study Of Medicaid Patients, Rachel Steward, Patricia Carney, Amy Law, Lin Xie, Yuexi Wang, Huseyin Yuce

Publications and Research

Objectives: The objectives were to compare the long-termoutcomes, including hysterectomy, chronic pelvic pain (CPP) and abnormal uterine bleeding (AUB), in women post hysteroscopic sterilization (HS) and laparoscopic tubal ligation (TL) in the Medicaid population.

Study design: This was a retrospective observational cohort analysis using data from the US Medicaid Analytic Extracts Encounters database.Women aged 18 to 49 years with at least one claimfor HS (n=3929) or TL (n=10,875) between July 1, 2009, through December 31, 2010, were included. Main outcome measures were hysterectomy, CPP or AUB in the 24 months poststerilization. Propensity score matching was used to control for patient …

Flow Anisotropy Due To Thread-Like Nanoparticle Agglomerations In Dilute Ferrofluids, Alexander Cali, Wah-Keat Lee, A. David Trubatch, Philip Yecko

Department of Applied Mathematics and Statistics Faculty Scholarship and Creative Works

Improved knowledge of the magnetic field dependent flow properties of nanoparticle-based magnetic fluids is critical to the design of biomedical applications, including drug delivery and cell sorting. To probe the rheology of ferrofluid on a sub-millimeter scale, we examine the paths of 550 μm diameter glass spheres falling due to gravity in dilute ferrofluid, imposing a uniform magnetic field at an angle with respect to the vertical. Visualization of the spheres’ trajectories is achieved using high resolution X-ray phase-contrast imaging, allowing measurement of a terminal velocity while simultaneously revealing the formation of an array of long thread-like accumulations of magnetic …

How Is Your Productivity Affected Based On Your App Usage?, Colette Noghreian

Student Scholar Symposium Abstracts and Posters

As technology becomes more prominent in society, it is crucial to investigate its effect on day to day life. The purpose of this study is to determine how the amount of time spent on iPhone applications affects how productive students feel in the span of one week. Results are tested through a survey which first determines general information about the student, and then guides students to navigate their phone settings and record the battery usage of the top three applications which use up the most battery. It is hypothesized that productivity decreases as battery usage increases due to the substantial …

Statistical Analysis Of Momentum In Basketball, Mackenzi Stump

Honors Projects

The “hot hand” in sports has been debated for as long as sports have been around. The debate involves whether streaks and slumps in sports are true phenomena or just simply perceptions in the mind of the human viewer. This statistical analysis of momentum in basketball analyzes the distribution of time between scoring events for the BGSU Women’s Basketball team from 2011-2017. We discuss how the distribution of time between scoring events changes with normal game factors such as location of the game, game outcome, and several other factors. If scoring events during a game were always randomly distributed, or …

Approximating The Distribution Of Indefinite Quadratic Forms In Normal Variables By Maximum Entropy Density Estimation, Ghasem Rekabdar, Rahim Chinipardaz

Journal of Modern Applied Statistical Methods

The quadratic form of non-central normal variables is presented based on a sum of weighted independent non-central chi-square variables. This presentation provides moments of quadratic form. The maximum entropy method is used to estimate the density function because distribution moments of quadratic forms are known. A Euclidean distance is proposed to select an appropriate maximum entropy density function. In order to compare with other methods some numerical examples were evaluated. Also, for discrimination between two groups by the Euclidean distances, we obtained a stochastic representation for the linear discriminant function using the quadratic form. The maximum entropy estimation was an …

Semi-Parametric Method To Estimate The Time-To-Failure Distribution And Its Percentiles For Simple Linear Degradation Model, Laila Naji Ba Dakhn, Mohammed Al-Haj Ebrahem, Omar Eidous

Journal of Modern Applied Statistical Methods

Most reliability studies obtained reliability information by using degradation measurements over time, which contains useful data about the product reliability. Parametric methods like the maximum likelihood (ML) estimator and the ordinary least square (OLS) estimator are used widely to estimate the time-to-failure distribution and its percentiles. In this article, we estimate the time-to-failure distribution and its percentiles by using a semi-parametric estimator that assumes the parametric function to have a half- normal distribution or an exponential distribution. The performance of the semi-parametric estimator is compared via simulation study with the ML and OLS estimators by using the mean square error …

Jmasm 48: The Pearson Product-Moment Correlation Coefficient And Adjustment Indices: The Fisher Approximate Unbiased Estimator And The Olkin-Pratt Adjustment (Spss), David A. Walker

Journal of Modern Applied Statistical Methods

This syntax program is intended to provide an application, not readily available, for users in SPSS who are interested in the Pearson product–moment correlation coefficient (r) and r biased adjustment indices such as the Fisher Approximate Unbiased estimator and the Olkin and Pratt adjustment.

Inferential Procedures For Log Logistic Distribution With Doubly Interval Censored Data, Yue Fang Loh, Jayanthi Arasan, Habshah Midi, M. R. Abu Bakar

Journal of Modern Applied Statistical Methods

The log logistic model with doubly interval censored data is examined. Three methods of constructing confidence interval estimates for the parameter of the model were compared and discussed. The results of the coverage probability study indicated that the Wald outperformed the likelihood ratio and jackknife inferential procedures.

On Poisson Quasi-Lindley Distribution And Its Applications, Razika Grine, Halim Zeghdoudi

Journal of Modern Applied Statistical Methods

This paper proposes a recent version of compound Poisson distributions named the Poisson quasi-Lindley (PQL) distribution by compounding Poisson and quasi-Lindley distributions. Some properties of the distributions are given with estimation and some illustrative examples.

Detection Of Outliers In Univariate Circular Data Using Robust Circular Distance, Ehab A. Mahmood, Sohel Rana, Habshah Midi, Abdul Ghapor Hussin

Journal of Modern Applied Statistical Methods

A robust statistic to detect single and multi-outliers in univariate circular data is proposed. The performance of the proposed statistic was tested by applying it to a simulation study and to three real data sets, and was demonstrated to be robust.

Modeling Agreement Between Binary Classifications Of Multiple Raters In R And Sas, Aya A. Mitani, Kerrie P. Nelson

Journal of Modern Applied Statistical Methods

Cancer screening and diagnostic tests often are classified using a binary outcome such as diseased or not diseased. Recently large-scale studies have been conducted to assess agreement between many raters. Measures of agreement using the class of generalized linear mixed models were implemented efficiently in four recently introduced R and SAS packages in large-scale agreement studies incorporating binary classifications. Simulation studies were conducted to compare the performance across the packages and apply the agreement methods to two cancer studies.

Jmasm 49: A Compilation Of Some Popular Goodness Of Fit Tests For Normal Distribution: Their Algorithms And Matlab Codes (Matlab), Metin Öner, İpek Deveci Kocakoç

Journal of Modern Applied Statistical Methods

The main purpose of this study is to review calculation algorithms for some of the most common non-parametric and omnibus tests for normality, and to provide them as a compiled MATLAB function. All tests are coded to provide p-values for those normality tests, and the proposed function gives the results as an output table.

The Impact Of Predictor Variable(S) With Skewed Cell Probabilities On Wald Tests In Binary Logistic Regression, Arwa Alkhalaf, Bruno D. Zumbo

Journal of Modern Applied Statistical Methods

A series of simulation studies are reported that investigated the impact of a skewed predictor(s) on the Type I error rate and power of the Wald test in a logistic regression model. Five simulations were conducted for three different regression models. A detailed description of the impact of skewed cell predictor probabilities and sample size provide guidelines for practitioners wherein to expect the greatest problems.

Jmasm 50: A Web-Based Shiny Application For Conducting A Two Dependent Samples Maximum Test (R), Saverpierre Maggio, Gokul Bhandari, Shlomo S. Sawilowsky

Journal of Modern Applied Statistical Methods

A web-based Shiny application written in R statistical language was developed and deployed online to calculate a new two dependent samples maximum test as presented in Maggio and Sawilowsky (2014b). The maximum test allows researchers to conduct both the dependent samples t-test and Wilcoxon signed-ranks tests on same data without raising concerns associated with Type I error inflation and choice of statistical tests (Maggio and Sawilowsky, 2014a). The maximum test in R statistical language provides a friendly user interface.

Jmasm 47: Anova_Hov: A Sas Macro For Testing Homogeneity Of Variance In One-Factor Anova Models (Sas), Isaac Li, Yi-Hsin Chen, Yan Wang, Patricia RodríGuez De Gil, Thanh Pham, Diep Nguyen, Eun Sook Kim, Jeffrey D. Kromrey

Journal of Modern Applied Statistical Methods

Variance homogeneity (HOV) is a critical assumption for ANOVA whose violation may lead to perturbations in Type I error rates. Minimal consensus exists on selecting an appropriate test. This SAS macro implements 14 different HOV approaches in one-way ANOVA. Examples are given and practical issues discussed.

A Remark For The Admissibility Of Rao’S U-Test, Z. D. Bai, C. R. Rao, M. T. Tsai

Journal of Modern Applied Statistical Methods

.

Front Matter, Jmasm Editors

Journal of Modern Applied Statistical Methods

.

Vol. 16, No. 2 (Full Issue), Jmasm Editors

Journal of Modern Applied Statistical Methods

.

'Parallel Universe' Or 'Proven Future'? The Language Of Dependent Means T-Test Interpretations, Anthony M. Gould, Jean-Etienne Joullié

Journal of Modern Applied Statistical Methods

Of the three kinds of two-mean comparisons which judge a test statistic against a critical value taken from a Student t-distribution, one – the repeated measures or dependent-means application – is distinctive because it is meant to assess the value of a parameter which is not part of the natural order. This absence forces a choice between two interpretations of a significant test result and the meaning of the test hypothesis. The parallel universe view advances a conditional, backward-looking conclusion. The more practical proven future interpretation is a non-conditional proposition about what will happen if an intervention is (now) applied …