Social and Behavioral Sciences Commons^™

Towards Interpretable Machine Reading Comprehension With Mixed Effects Regression And Exploratory Prompt Analysis, Luca Del Signore

Dissertations, Theses, and Capstone Projects

We investigate the properties of natural language prompts that determine their difficulty in machine reading comprehension tasks. While much work has been done benchmarking language model performance at the task level, there is considerably less literature focused on how individual task items can contribute to interpretable evaluations of natural language understanding. Such work is essential to deepening our understanding of language models and ensuring their responsible use as a key tool in human machine communication. We perform an in depth mixed effects analysis on the behavior of three major generative language models, comparing their performance on a large reading comprehension …

Vietnam’S Gdp: Re-Assessing Growth Rate And Identifying An Alternative Indicator, My Linh D. Nguyen

Honors Theses

Since the economic reform known as Doi Moi (Renovation) in 1986, Vietnam has changed from one of the world’s poorest to a middle-income country in one generation (USAID, 2022). The country has consistently registered high and stable economic growth since the reform, averaging 6.3% from 1985 to 2021 (World Bank, 2022). High growth rate of gross domestic product (GDP) is good news, but it has also raised questions that go both ways. On one side, there is much speculation that the government of Vietnam has manipulated economic statistics, compared to the case of China and India. As quoted in Kinh …

Towards Scalable Mental Health: Leveraging Digital Tools In Combination With Computational Modeling To Aid In Treatment And Assessment Of Major Depressive Disorder, Matthew D. Nemesure

Dartmouth College Ph.D Dissertations

Major depressive disorder (MDD) is a debilitating disorder that impacts the lives of nearly 280 million individuals worldwide, representing 5% of the overall adult population. Unfortunately, these statistics have been both trending upward and are also likely an underestimate. This can be primarily attributed to lack of screening paired with a lack of providers. Worldwide, there are roughly 450 individuals living with MDD per mental health care provider. Adding to this burden, approximately half of affected individuals that do receive care of any kind will fail to remain in remission. The goal of this thesis work is to leverage statistical …

Forecasting Razorback Baseball Game Outcomes, Austin Raabe

Information Systems Undergraduate Honors Theses

Despite the disappointing end to the 2021 Arkansas Razorback baseball year, the team’s success provided hog fans something to look forward to next season. While they will be without the 2021 Golden Spikes Award winner, Kevin Kopps, and four All-SEC team selections, the 2022 roster has promising new and returning talent. With fifty percent of the players who played significant time last year coming back (minimum ten hits or ten innings pitched), the arrival of several impact transfers from major conferences, and a recruiting class ranked in the top five according to Perfect Game, there is reason to believe that …

Factors Affecting Graduation With Honors: A Case Study In Business, William Litzinger

Agricultural Economics and Agribusiness Undergraduate Honors Theses

Many first-year college students elect to enroll in their university’s honors program. These programs offer students many educational benefits not provided to non-honors students, such as smaller class sizes, priority registration, and added faculty interaction. However, of the students that enter the university as an honors student, many fail to complete their honors program. Researchers have documented completion rates as low as 18.45% (Campbell and Fuqua, 2008). So why are honors graduation rates so low? In this study, variables were examined that the literature suggests affects honors graduation rates (High School GPA, ACT/SAT scores, AP credits, GPA 1^st term …

Understanding And Improving The System: The Effects Of Weighting On The Accuracy Of Political Polling In Arkansas, Beck Williams

Political Science Undergraduate Honors Theses

In an effort to increase the accuracy of statewide political polling in Arkansas, we explore the statistical strategy of weighting with a focus on one yearly opinion poll: The Arkansas Poll. We conduct over 70 weighting experiments on the 2016 and 2020 Arkansas Polls using a variety of variables and opinion questions. From these experiments, we find that while some weighted variables tend to create larger changes, weighting typically results in a single-digit percentage change that does not substantially shift or “flip” the majorities. Due to a greater rate of change through weighting in the 2020 Poll compared to the …

Analytical Study To Determine Significant Causes Of Increased No-Hitters In The 2021 Major League Baseball Season, Joel Robison

Honors Projects

Why were there so many no-hitters in the 2021 MLB season? This project focuses on possible significant causes to the record-breaking number of no-hitters pitched in the 2021 Major League Baseball season. Specifically, this project takes an analytical look at the recent trends in launch angles and spin rates to determine if there are any significant causes to the increased number of no-hitters in baseball. The random nature and unpredictability of the game of baseball make it almost impossible to come to any solid conclusions.

A Monte Carlo Simulation Of Rat Choice Behavior With Interdependent Outcomes, Michelle A. Frankot

Graduate Theses, Dissertations, and Problem Reports

Preclinical behavioral neuroscience often uses choice paradigms to capture psychiatric symptoms. In particular, the subfield of operant research produces nested datasets with many discrete choices in a session. The standard analytic practice is to aggregate choice into a continuous variable and analyze using ANOVA or linear regression. However, choice data often have multiple interdependent outcomes of interest, violating an assumption of general linear models. The aim of the current study was to quantify the accuracy of linear mixed-effects regression (LMER) for analyzing data from a 4-choice operant task called the Rodent Gambling Task (RGT), which measures decision-making in the context …

What Is This Noise?: A Comparison Of Narrative And Statistical Program Notes' Ability To Affect Enjoyment, Luke Henderson

Theses

Program notes, brief written statements provided to attendees of classical music performances, have in some cases increased audiences’ enjoyment of what they hear, but results from such research are inconsistent. This study sought to explore the effects of program notes on enjoyment, eudaimonic appreciation, and intention to attend a concert, as well as whether narrative or statistical styles of notes would be more effective. Participants in an experiment were randomly assigned to one of three conditions--no program notes, narrative style program notes, and statistical program notes--then asked to listen to a piece of music. Those who received program notes reported …

A Geospatial And Statistical Analysis Of Dropout In Louisiana Public High Schools, Michael D. Stein

LSU Master's Theses

Students dropping out of high school is a nationwide problem, plaguing communities and often greatly reducing the prospects of a quality life for those students who do not complete their high school educations. Louisiana consistently has among the highest public high school dropout rates in the United States, and often the highest. This geospatial and statistical study aims to identify the factors that correlate with high school dropout in Louisiana public high schools, specifically, and to produce detailed maps of the dropout rates across the state to identify the schools most afflicted.

Extensive school-level data from five academic years (2014-15 …

Extreme Cold Event Perception And Preparedness Of Western Michigan University Students, Connor J. Landeck

Masters Theses

Preparing for disasters at universities differs throughout the country but taking preventative measures is the first step in reducing loss of life and recovery measures. This research examined differences among undergraduate students regarding perceptions when it comes to extreme cold events at Western Michigan University (WMU). The main focus of the thesis was to determine if there is a lack of awareness and/or preparation measures of extreme cold events. Data were collected online using a specially designed questionnaire through Qualtrics. Survey questions were coded and analyzed using SPSS software using standard univariate descriptive statistics and/or multivariate statistical tests deemed appropriate. …

Examining How Adverse Childhood Experiences And The Underlying Processes Of Trait And State Impulsivity Influence Suicidal Behavior, Julia K. Duran

Master's Theses

ABSTRACT

Due to the effects of ACEs and impulsive behavior on mental and physical health, it is important to better understand the relationship between these two as well as how they both may influence choices, such as suicide. Numerous studies have identified impulsive behavior as a risk factor for suicide, however, recent research has identified several underlying independent processes that make up impulsivity. This study uses a broad assessment of trait and state impulsivity to gather a more discrete understanding of the underlying processes that contribute to impulsive behavior. The short version UPPS-P scale was used to measure negative urgency, …

Assessing And Forecasting Chlorophyll Abundances In Minnesota Lake Using Remote Sensing And Statistical Approaches, Ben Von Korff

All Graduate Theses, Dissertations, and Other Capstone Projects

Harmful algae blooms (HABs) can negatively impact water quality, lake aesthetics, and can harm human and animal health. However, monitoring for HABs is rare in Minnesota. Detecting blooms which can vary spatially and may only be present briefly is challenging, so expanding monitoring in Minnesota would require the use of new and cost efficient technologies. Unmanned aerial vehicles (UAVs) were used for bloom mapping using RGB and near-infrared imagery. Real time monitoring was conducted in Bass Lake, in Faribault County, MN using trail cameras. Time series forecasting was conducted with high frequency chlorophyll-a data from a water quality sonde. Normalized …

Southwest Pacific Tropical Cyclone Frequency And Intensity Related To Observed And Modeled Geophysical And Aerosol Variables, Rupsa Bhowmick

LSU Doctoral Dissertations

The dissertation focuses on western region of Southwest Pacific Ocean (SWPO)

basin (135E - 180, and 5S - 35S) tropical cyclone (TC) climatology using observed

and modeled data. The classification-based machine learning approach

identifies the synoptic geophysical and aerosol environment favorable or unfavorable

for TC intensification and intensity change prior to landfall incorporating

observational and satellite data. A multiple poisson regression model with varying

temporal monthly lags was used to build a relationship between the number of

monthly TC days with basin wide average dust aerosol optical depth (AOD), sea

surface temperature (SST), and upper ocean temperature (UOT). This idea …

Neural Mechanisms Of Cognitive Individual Difference: An Investigation Of The Human Connectome Project, Shelly Renee Cooper

Arts & Sciences Electronic Theses and Dissertations

Considering individual differences in task activation functional magnetic resonance imaging (t-fMRI) can be challenging because they may arise from variability in activity in brain regions, in the tasks themselves, or some combination thereof. Delineating sources of between-subjects variance is particularly important for cognitive control where task goals are at the forefront. Here we applied structural equation modeling (SEM) to the Human Connectome Project to examine if activity could be partitioned into separable brain and task individual difference dimensions. A series of SEMs were defined with varying numbers of latent factors, where the inputs were parcels of two cognitive control-related brain …

Boom Or Bust: Examining The Relationship Between High School Recruiting Rankings And The Nfl Draft, Nicholas E. Tice

Senior Theses

The goal of this thesis is to model the probability of a high school football player’s chance of being drafted based on information taken from their recruiting profile. The response variable is binary and defined as drafted (1) or undrafted (0). The independent variables were collected by scraping data from the recruiting websites including height, weight, position, hometown, recruiting grade and other socioeconomic factors based on the player’s high school. 247Sports and ESPN were the two recruiting services used and compared in this study. Because of the binary nature of the dependent variable, logistic regression and decision trees were chosen …

Advanced Statistics In Arkansas Sports Reporting, Andrew Lee Epperson

Graduate Theses and Dissertations

This study seeks to analyze how Arkansas’ sports journalists are adapting to the recent surge in available advanced statistics that are being used by certain national news organizations. Using in-depth qualitative research that includes in-depth interviews with a number of individuals in the print, broadcast, and athletics side of sports coverage, we discover how journalists and coaches use these next-generation analytics, what they fundamentally mean for the evolution of each respective path, and why so few Arkansas reporters and writers use them at the time of this paper’s defense. We see how budgets and deadlines restrict the use of these …

A Brief Statistical Introduction Of The Global Refugee Problems With Data Analysis, April Yan Zhang

Honor Scholar Theses

No abstract provided.

Application Of Geodetector Method And Other Statistical Methods To Study Groundwater Vulnerability To Nitrate Contamination In The Central Valley Aquifer, California, Anil Shrestha

Graduate Research Theses & Dissertations

The Central Valley (CV) Aquifer, California is one of the most productive regions of the United States, where large amount of nitrogen fertilizer has been applied for the last few decades to increase the crop productivity. The application of excessive fertilizer has increased the level of nitrate (NO3-N) in the groundwater to above EPA’s maximum contamination level (MCL) of 10 mg/L in several domestic, public and monitoring wells. The concentration of nitrate in the groundwater can vary spatially depending on the local nitrogen sources, aquifer characteristics and geochemical condition of the area. The changing hydrogeological conditions of the valley due …

Strong Side, Weak Side: Goal Generating Tactics In Ncaa Men's Water Polo, Joey Gullikson

University of the Pacific Theses and Dissertations

In the game of water polo, it is generally accepted that the shooting position of the offensive player and the tactic employed are both important in generating goals. Despite their importance, little is known about the relationship between shooting position and offensive tactics and their impact on the probability of goal scoring. In this research, a sequence of hierarchical mixed logistic regression models is applied to a unique data set from 2016 and 2017 NCAA men’s water polo seasons to analyze the relationship between goal generating tactics and different shooting positions. The primary result reveals that the closer a player …

A 3d Characteristics Database Of Land Engraved Areas With Known Subclass, Entni Lin

Student Theses

Subclass characteristics on bullets may mislead firearm examiners when they rely on traditional 2D images. In order to provide indelible examples for training and help avoid identification errors, 3D topography surface maps and statistical methods of pattern recognition are applied to toolmarks on bullets containing known subclass characteristics. This research was conducted by collecting 3D topography surface map data from land engraved areas of bullets fired through known barrels. This data was processed and used to train the statistical algorithms to predict their origin. The results from the algorithm are compared with the “right answers” (i.e. correct IDs) of the …

Social Organization And Environmental Patterning At Tel Abu Shusha: An Integrated Spatial Approach To Survey Archaeology, Seth Price

Graduate Theses and Dissertations

Tel Abu Shusha, located in the Jezreel Valley of Palestine, is a large-scale archaeological site possibly identified as the cities of Biblical Gaba or Roman Gaba Hippaeon/Gaba Philippi. Surface archaeological survey of the surrounding area, conducted by the Jezreel Valley Regional Project during 2017, revealed extensive assemblages of visible settlement features dating primarily to middle and late Islamic periods. This research seeks to answer questions of settlement decision-making and societal organization, by integrating archaeological, textual, environmental, and geospatial data sources. In addition to visual interpretation, Kolmogorov-Smirnov nonparametric tests are used to gain insight on environmental settlement preferences; Ripley’s K analysis …

Marginal Mediation Analysis: A New Framework For Interpretable Mediated Effects, Tyson S. Barrett

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Mediation analysis is built to answer not only if one variable affects another, but how the effect takes place. However, it lacks interpretable effect size estimates in situations where the mediator (an intermediate variable) and/or the outcome is categorical or otherwise non-normally distributed. By integrating a powerful approach known as average marginal effects within mediation analysis—termed Marginal Mediation Analysis (MMA)—the issues regarding categorical mediators and/or outcomes are, in large part, resolved. This new approach allows the estimation of the indirect effects (those effects of the predictor that affect the outcome through the mediator) that are interpreted in the same way …

Does Player Performance Outside Of Major League Baseball Translate To The Mlb?, Ian Vogt

Honors Theses

Statistical analysis has transformed the way front offices across Major League Baseball manage the rosters of their teams. However, much of this statistical analysis is limited to evaluating players playing in the American major league environment. Little has been done in the way of using statistical analysis to evaluate how performance translates from league-to-league, and the market for international and college players remains highly inefficient, despite expansion of these player pools. My study is an attempt to make this market a more efficient one.

I measure the correlation between performance in two top international baseball leagues (Nippon Professional Baseball and …

Abandoned By Home And Burden Of Host: Evaluating States' Economic Ability And Refugee Acceptance Through Panel Data Analysis, Ummey Hanney Tabassum

Browse all Theses and Dissertations

This research examines the relationship between the number of refugees hosted by states and the economic ability of host states by using UNHCR’s refugee data and World Bank’s GNI per capita data. To identify the relationship between these two variables, this study uses two sets of panel data covering 145-178 countries, around 43-55 years and 3000-5000 observations. For the two sets of panel data, four models are produced to test the null and alternative hypotheses. In all four cases, results show that there is a statistically significant negative correlation between the number of refugees hosted by states and GNI per …

The Effect Of Unemployment On Democratic Warfare, Andres Rakower

Honors Undergraduate Theses

This study was done to see the effects of a war on the economy and the internal politics of the United States. In selecting the engagement, we would study we agreed the Iraq War would be aided by a large amount of sampling of public opinion that was more nuanced than in previous wars. The Iraq War was a very complicated war, as it was controversial from the beginning and became a political issue while continuing to be a war fought by Americans abroad. Based on the literature, there were many starting effects and assumptions that were accounted for such …

Assessing The Implicitness Of Visual Statistical Learning At The Individual Level, Derek Mcclellan

Online Theses and Dissertations

Previous research has examined visual-statistical learning at the individual level but have used measurements which are not sensitive enough to detect differences at the individual level. This study investigates temporal visual-statistical learning but uses a recently modified task designed to be more sensitive to individual performance. This study also incorporated an indirect measure of learning in the form of a rapid serial visual presentation paradigm (RSVP), a cover task, and binary confidence judgments, to assess how aware participants were of the statistical structure. Although there was strong evidence of participants learning the statistical structure at the group level, there was …

Teaching Introductory Statistics To Graduate Students In The Social Sciences: A Mixed Method Investigation Of The Effectiveness Of Simulations In Statistics Education, Liuli Huang

LSU Doctoral Dissertations

The primary purpose of this study is to determine the effectiveness of using simulations as an instructional tool in an introductory doctoral level statistics course. The study focuses on the impacts of simulations on students’ attitudes and understanding of statistical concepts, as well as how the simulations could inspire students’ positive attitudes and improve statistics performance or would fail to help. In addition, since the statistics anxiety has been a primary obstacle to students’ statistics education, and “statistics anxiety” is experienced by as many as 80% of graduate students (Onwuegbuzie, 2004). The researcher is interested to explore the details of …

Defining Data Science And Data Scientist, Dana M. Dedge Parks

USF Tampa Graduate Theses and Dissertations

The world’s data sets are growing exponentially every day due to the large number of devices generating data residue across the multitude of global data centers. What to do with the massive data stores, how to manage them and defining who are performing these tasks has not been adequately defined and agreed upon by academics and practitioners. Data science is a cross disciplinary, amalgam of skills, techniques and tools which allow business organizations to identify trends and build assumptions which lead to key decisions. It is in an evolutionary state as new technologies with capabilities are still being developed and …

Bayesian Approach To Toolmark Analysis, Antonio W. Del Valle

Student Theses

Statistical analysis of toolmarks using frequentist methods can be problematic for assorted reasons. Thus, in order to analyze toolmarks whilst avoiding these issues, a Bayesian approach is taken. Specifically for this thesis we discuss the computation of a specific Likelihood Ratio for toolmark comparisons. This Bayesian based approach involves using data already at hand in conjunction with a probability model in order to establish an estimate for its “value”, i.e. the “weight of evidence”. Making the calculations to obtain a Likelihood Ratio is very cumbersome and time consuming. Also many commercial software packages hide the process and underlying assumptions that …