This project presents a multiple linear regression analysis of mentally unhealthy days among U.S. adults using the 2023 Behavioral Risk Factor Surveillance System (BRFSS) data (n = 8,000). The analysis examines how physical health, BMI, sex, exercise, age, income, education, and smoking status predict self-reported mentally unhealthy days in the past 30 days. Key components include full model estimation with coefficient interpretation, Type III partial F-tests, chunk tests for income and education, and an interaction analysis exploring whether the association between current smoking and mental health differs by sex. Findings are visualized through adjusted predicted marginal means with 95% confidence intervals. All data processing, recoding, and modeling were conducted in R using tidyverse, broom, gtsummary, car, and ggeffects.

This project consists of using the New York Times Article Search API to examine how the volume and framing of soccer coverage in the New York Times has evolved since the modern Major League Soccer (MLS) expansion era began in 2005.In fact d,API provides rich article-level metadata such as headline, publication date, section name, news desk, word count, and multimedia flags since 1851, making it well suited for detecting decade-long window in editorial attention and story framing by querying the keyword “soccer”

An analysis of global wellbeing data from 153 countries, exploring the relationships between economy, health, freedom, job satisfaction, and corruption on national happiness scores.

This report presents a guided walkthrough and in-class lab activity from EPI 553 (Statistical Inference), exploring the use of dummy variables in multiple linear regression using the Behavioral Risk Factor Surveillance System (BRFSS) 2020 dataset (n = 5,000). The analysis investigates how general health status and educational attainment are associated with the number of mentally unhealthy days in the past 30 days, after adjusting for age, sex, physical health days, and sleep hours. Topics covered include the failure of naive numeric coding for categorical predictors, construction and interpretation of dummy variables, reference group selection and re-leveling, the dummy variable trap, partial F-tests for overall categorical variable significance, Type III ANOVA, and alternative coding schemes including effect coding and orthogonal polynomial contrasts. All analyses were conducted in R using tidyverse, broom, gtsummary, car, and ggeffects.