Data Analysis
May 2025 - Present
Research Assistant
Github, Python, Excel, Zoom
I collaborated with two researchers to analyze multi-source datasets (Excel/CSV/DBF), engineer features, and model performance across locations. I built Python pipelines to merge files, generate new variables, and evaluate OLS/LASSO models and correlation matrices. Deliverables included reproducible code, model diagnostics, and plain-language insights for stakeholders.
My goal was to take data from excel, csv, and dbf files and organize or generate new data from them. To get to the end goal, I needed to create code to read the files and match different data together. I ran regression models, lasso, and correlation matrixes with this data. Oftentimes new variables were created to further explain our models. This research will be published. More information on this page will be available once published.