Course Projects

Statistical Computing: C++ Implementation of GuanRank

• Synopsis: We implemented GuanRank (Non-parametric algorithm to transform censored survival data to hazard ranks) in C++ to improve computational speed and memory efficiency. Our C++ version vastly outperforms a python implementation of GuanRank.

Biostat 615 Report Here

Longitudinal and Correlated Data Analysis: Analyzing Longitudinal Student Grades Using a Mixed Effects Model

• Synopsis: We wanted to identify factors affecting middle school student math scores over their three years. To account for correlated outcomes, we implemented a linear mixed effects model with a random intercept and slope.

Biostat 653 Report Here

Bayesian Inference: Analyzing Bike Rental Data using a Bayesian Framework

• Synopsis: We wanted to identify factors affecting the number of bike rentals in Washington DC. Using a bayesian framework, we implemented a poisson regression with a spike and slab prior to perform variable selection by inspecting the posterior means for each predictor.

Biostat 682 Report Here