Practice
Most analytics work is judged by how it reads. I build mine to be judged by how well it holds up under audit, replication, and a critical reader. Assumptions are documented. Models are validated the right way. Code is handed off in a form your team can actually rerun.
Engagements are bounded — project-based or short retainer — and every one starts with a scoping conversation and a written proposal. Nothing gets billed without a deliverable behind it.
Where I trained
M.S. Statistics
2022 – 2024
Bayesian methods, experimental design, and applied multivariate modeling. Taught undergraduate sections and modernized the department's data-visualization curriculum with Quarto, webR, and reproducible Shiny labs.
Department of StatisticsM.S. Data Science
2021 – 2022
Machine learning, predictive modeling, and reproducible analytics workflows. Team capstones on real datasets across retail, census, and healthcare gave the program its applied edge.
Data Science programB.S. Mathematics
2016 – 2020
Calculus, linear algebra, probability, and the analytical foundations everything else sits on. First exposure to statistical computing and the habits of careful proof.
Visit LinfieldThe full coursework list, advisors, and teaching record is on the resume.
Independence
I'm currently employed as a Business Intelligence Analyst at the Oregon Department of Education. Epsilon Labs is operated independently of that role. I do not accept engagements that conflict with my day-job responsibilities, and I decline work that touches the same data systems or stakeholders.
