Hello, I’m Nick. Welcome to my professional and academic portfolio website.
I completed my M.S. in Statistics at UCLA and am currently planning to go back to school for a PhD in Statistics beginning in Fall 2026.
In my research, I’m interested in a wide array of ideas lying at the intersection of statistics and applied mathematics. My primary interests lie in Bayesian modeling and inference, with particular emphasis on inverse problems, uncertainty quantification, and Bayesian data assimilation. I am also interested in probabilistic modeling frameworks that incorporate mathematical structure, including stochastic processes, spatial and spatiotemporal statistics, and functional data analysis.
I have experience in building tools like data dashboards and statistical learning models to help uncover meaningful insights about data, including performing statistical/machine learning research in academia. I try to maintain and continually expand a diverse, up-to-date set of data analysis and research skills; in particular I specialize in Python, R, SQL (PostgreSQL), and frameworks like Dash and Flask for data dashboard applications and visual storytelling.
I’m also very passionate about statistics and mathematics education. I produce instructive videos and articles explaining core concepts, discussing interesting historical uses of statistics, and exploring more niche advanced topics. I also work as a tutor part-time, which gives me the opportunity to help high school and college students grow their mastery (and hopefully appreciation!) of stats and math.
(Note: I am continuously trying to consolidate all of my work here—which often feels scattered all over the place—on this website, so some things may be temporarily missing or incomplete. Work is ongoing! )
You can find quick links to my statistics research, data science projects, and other work I’ve done on my Projects page and at my GitHub.
Projects
- Data-Centric Machine Learning (Synthetic Data) Research
- An investigation into auditing the true privacy benefits of the use of synthetic data in sensitive domains such as healthcare, incorporating generative models for producing datasets and adversarial attack frameworks to assess (differential) privacy versus downstream model utility.
- Bayesian Inverse Problems for ODE Systems under Model Misspecification
- Theoretical and applied investigations into the effects of Bayesian model misspecification on statistical inference in nonlinear ordinary differential equations and dynamical system models (e.g., SIR, Lotka–Volterra, and their extensions) using Python/PyMC.
- Founding Fathers Correspondence Network
- An ongoing initiative to analyze and gain new data-driven insights into early writings and letters of early American historical figures via spatiotemporal and network data analysis and visualizations of correspondence patterns during the founding era.
Notes
This website was built using Quarto.
Email: