Here are some of my projects and work samples. My favorite statistical applications are business, basketball, and biotech.

Personal Projects

Graduate Projects

Do Bad Yelp Reviews Cause Closure?

(Causal inference, machine learning)
Yelp reviews certainly guide my choice of restaurant. Bland flavors? Tough steak? Count me out! While Yelp reviews do keep some customers away, in this project we conclude that according to our Las Vegas data Yelp reviews do not cause closure (under assumptions, see our report and slides).

Gene Expression Signatures of Endometriosis

(Genomics, machine learning)
Endometriosis is an estrogen-dependent condition that affects nearly 10% women of reproductive age and is characterized by chronic pain and inflammation. In this genomics project, our team explored, built, and evaluated machine learning models on their ability to identify subjects with endometriosis based on gene expression intensity alone to contest models currently in literature. We improved upon our predictions using SuperLearner ensemble learning. See our report (2018), slides (2019), and Git repository.

Undergraduate Projects

Data & Web Technologies for Data Analysis (STA 141B)
- White House Petitions (NLP, machine learning)
- San Francisco Data (SQL, maps)
Categorical Data Analysis (STA 138)
- Baby Dataset (Logistic Regression)
- School Dataset (Multinomial Logistic Regression)