Title: Review - Muscular adaptations and insulin-like growth factor-1 responses to resistance training are stretch-mediated
Abstract: Muscular Hypertrophy training is the use of resistance training to cause damage to muscle tissue cells to stimulate the adaption process and make them bigger. The scientific understanding of hypertrophy has increased exponentially over the past few decades. The article Muscular adaptations and insulin-like growth factor-1 responses to resistance training are stretch-mediated shows just how influential technique can be. This article performed a thorough experiment and analysis to provide evidence that indicates loading muscles at a fully lengthened position is significantly more hypertrophic than shortened muscle positions. Given this information, it is clear that utilizing a full range of motion that accentuates the stretched position of a muscle is optimal for maximizing the hypertrophy of that muscle.
Title: The Statistical Writing Process
Reference: Chapters 3-4 of Statistical Writing: https://statds.github.io/stat-writing/.
Title: Article Review - A qualitative examination of the impacts of financial stress on college students’ well-being
Abstract: Students pursuing higher education often face significant challenges, particularly regarding financial stress, which can profoundly impact their academic performance and overall well-being. This presentation provides a comprehensive review of a recently published article, “A qualitative examination of the impacts of financial stress on college students’ well-being,” authored by {Moore et al. (2021)}. The study, conducted at a large, private institution, inspects the complex relationship between financial stress and various aspects of the college experience, including academic performance, social well-being, and mental health. This presentation aims to show some of the challenges encountered by many college students today due to financial constraints. By comparing these findings with established data from the University of Connecticut, the goal is to gain deeper insights into the repercussions of financial stress on students and their applicability to the local community.
Title: Review - Odds Estimating with Opponent Hand Belief for Texas Hold’em Poker Agents
Abstract: As we all know, Texas Hold’em is currently the most popular poker game, and the most important thing in Texas Hold’em, besides analyzing the psychology of other people at the table, is to understand the probability of your own hand beating the hands of other competitors. The paper I am analyzing today provides three different win rate algorithms based on the analysis of various hand combinations to assist in decision-making. These methods are the expected win rate algorithm with start hand range (EWR-SHR), the expected win rate algorithm with fold rate (EWR-FR), and the expected win rate algorithm with opponent hand distribution (EWR-HD). These methods improve the accuracy of win rate estimation by combining the opponent model and observed actions to predict the opponent’s hand range or distribution. I will explain the models of various win rate algorithms through this article and display the data model. Finally, I will summarize the reliability and possible uses of these algorithms through the data in this article.
Title: Improving the Methodology of Court Decision Analysis Modeling
Abstract: The legal system is complicated with many factors playing a role within determining court decisions. If we were to use data to perform an analysis on court decisions, what exactly would that look like? Some of the common datasets collected in order to investigate this are chosen based upon answering how the area of the court, judges of the court, and the defendant may impact the verdict, which each might contain variables that are collected for multiple of those (i.e., race, gender) or specific to a particular category (i.e., previous convictions is specific to defendant data). That brings in the question of how to structure a model that can assess these variables correctly, and although some research has already been done where applications, typically a regression analysis, are done to test for any linear relationships, there is a lot of evidence that suggests that the predictors need to be grouped into independent hierarchical levels, since the differences in areas as well as judges should be considered separately, possibly through a multilevel regression.
Reference: Dhami, Mandeep K., and Ian Belton. “Statistical Analyses of Court Decisions: The Example of Multilevel Models of Sentencing.” Law and Method 10 (2016): 247-266. https://www.bjutijdschriften.nl/tijdschrift/lawandmethod/2016/10/lawandmethod-D-15-00011.pdf
Title: Markov Chains and their Applications to Baseball
Abstract: Everyone who watches or pays attention to baseball/most sports in general knows just how critical the underlying numbers are. And with these underlying numbers we can often help predict, understand, and attempt to strategize how future games will go for the team and/or individual players. As seen in the study I will be discussing, the stochastic process known as Markov chains can be strongly and usefully applied to predicting outcomes in baseball games [at least at the collegiate level]. I will begin the presentation with a brief overview of Markov chains and some of their properties; as the class Stochastic Processes is not a mandatory course in the Statistics Coursework. I will then explain how certain types of Markov chains like absorbing Markov chains and their properties can be applied to predict the outcomes of baseball games [the writer of this paper predicted games for their college at the college of Wooster]. These Markov Chains are going to be used to demonstrate how one can predict the amount of runs the college of Wooster will score on average per game; then will be applied to understanding whether or not this works for individual performance as well. The presentation then will conclude how certain Markov chains can be used to implement and advise certain strategical plays by an individual team/player.
Title: The Application of Statistics in Daily Life.
Abstract: My presentation delves into the pervasive influence of statistics across various sectors, emphasizing its critical role in data interpretation, decision-making, and research advancement. Through illustrative examples, it elucidates fundamental statistical principles such as descriptive and inferential statistics, hypothesis testing, Bayes’ Rule, and multiple regression analysis. Highlighting the practical application of these concepts in everyday scenarios, the text underscores the indispensable nature of statistical literacy in comprehending and leveraging data to inform decisions in a data-driven world.
Title: Quantitative Methods and Statistical Analytics in Public Policymaking
Abstract: Statistical and data analytics have recently gained transformative roles in informing evidence-based decision making, including within social research and thereby policymaking. This presentation considers the variables typically captured in big data and examines the quantitative methodologies used in statistical and data analysis, showcasing its capacity to uncover intricate patterns and correlations within society. It explores diverse sources of social data, including surveys, polls, social media, and government records, and how they facilitate the extraction of nuanced insights into societal risks and issues, particularly within demographic differences. This presentation considers the power of statistical data analytics in assessing public sentiments, policy effectiveness, and demographic-specific impacts, emphasizing the benefit of policymakers integrating social scientists’ complex correlations and findings into actionable policies.
- Hossin, M. A., Du, J., Mu, L., & Asante, I. O. (2023). Big Data-Driven Public Policy Decisions: Transformation Toward Smart Governance. SAGE Open, 13(4). https://doi.org/10.1177/21582440231215123.
- Suominen, A., & Hajikhani, A. (2021). Research themes in big data analytics for policymaking: Insights from a mixed-methods systematic literature review. Policy Internet, 13, 464–484. https://doi.org/10.1002/poi3.258.
- Sheng, J., Amankwah-Amoah, J., Khan, Z. and Wang, X. (2021), COVID-19 Pandemic in the New Era of Big Data Analytics: Methodological Innovations and Future Research Directions. Brit J Manage, 32: 1164-1183. https://doi.org/10.1111/1467-8551.12441.
Title: How to format your Research Paper
Abstract: With the project proposals coming up it is helpful to know what exactly is demanded by each section of the research paper. This presentation focuses on chapter 4 of the textbook which entails formatting and content suggestions for each one of the sections of the research paper. Additionally, this chapter of the online textbook provides some tips regarding the flow and use of word tenses for research papers as well as rules for how to avoid abusing key terms in statistics. The importance of this chapter is conveyed by its thorough description of how to make professional and presentable publication of your research results. The intention is for viewers to leave to take this advice and apply it not only to their upcoming projects but towards any other publications they may participate in.
Link to slides: https://docs.google.com/presentation/d/1Hjy_eS7NtkWO4j55H20iJQHIcj5VRAas35JJClWLQU8/edit?usp=sharing.
Title: Prediction of Obesity Level by Using K-Neighbors Classifier and Decision Tree Model
Abstract: This research analyzes a publicly available dataset on Amazon AWS, including gender, age, eating, smoking, and other lifestyle feature. Two methods are selected to predict the obesity level: K-neighbor classifiers can fit the data, train a simple and effective classification model and identify common features of people with different obesity levels; random forest classifier in the decision tree model can handle input samples with high-dimensional features and has good predictive performance, the model parameters can also explore the factors that have big impact on obesity levels. Through these explorations, we can effectively guide the factors that contribute to obesity and assess the possibility of individual obesity.
Title: European Soccer Match Outcome Prediction
Abstract: This research aims to outperform bookmaker odds and achieve a profitable return on investment by using a comprehensive soccer dataset obtained from Kaggle. The dataset includes over 25,000 international matches, player statistics from FIFA, and betting data from 2008 to 2016 across 11 European countries. Our methodology integrates data exploration, visualization and advanced machine learning techniques. We utilized and compared Random Forest and Logistic Regression models to forecast match outcomes, and evaluated models accuracy. Moreover, we also explored the impact of regularization in Logistic Regression and emphasized the significance of cross-validation in model evaluation. This study emphasizes the importance of cross-validation in validating model performance. Through this analysis, we expect to explore the potential of strategic betting decisions, gain a deeper understanding of soccer match dynamics, and demonstrate the practical applications of machine learning in sports analytics.
Title: The Impact of Recommender Systems on User Behavior and Information Propagation in Social Networks
Abstract: Recommender systems play an important role in influencing user experiences and information distribution in social networks. This study dives into the complex dynamics of how recommender systems impact user behavior and content dissemination across social media platforms. It investigates the mechanisms by which personalized suggestions impact user perceptions and actions, focusing on the balance between tailored information distribution and maintenance of variety and fairness within social networks. The investigation considers a variety of factors, including information filtering, user engagement, and the privacy concerns of tailored suggestions. By studying these patterns, this study hopes to gain insight into the complex influence of recommender systems on social network dynamics and user interactions.