Jonah聽Gabry
Statistician
New York, New York, United States
Summary
馃ぉ
Rockstar馃帗
Top SchoolJonah Gabry is a statistician with 11 years of experience focused on Bayesian modeling and Stan development at Columbia University鈥檚 Applied Statistics Center. He combines academic rigor with practical software engineering, contributing significant enhancements to widely used projects like brms, rstan, and the tidymodels broom package to improve MCMC tidying, diagnostics (Rhat/ESS), and plotting. His work shows attention to reproducible workflows and dependency reduction, such as refactoring to remove reshape2 and tightening unit tests and log-likelihood calculations. Based in New York, he translates complex Bayesian methods into reliable tools and examples that make model comparison and diagnostics more accessible to applied researchers.
11 years of coding experience
University of PennsylvaniaColumbia University in the City of New YorkUniversidad de Playa Ancha de Ciencias de la Educaci贸nB.A., B.A. at Bowdoin College
Github Skills (13)
tidy10
bayesian-statistics10
mcmc10
bayesian10
stan10
statistical-models10
r-package10
bayesian-inference10
modeling10
cross-validation10
r10
tidyr10
ggplot9
Programming languages (10)
Github contributions (5)
stan-dev/rstan
Aug 2015 - Nov 2021
RStan, the R interface to Stan
Role in this project:
Back-end Developer
Back-end DeveloperContributions:3 reviews, 178 commits, 30 PRs in 6 years 3 months
Contributions summary:Jonah's commits primarily focus on refactoring the `rstan` package by removing the use of the `reshape2` package. This suggests a focus on streamlining the codebase, potentially for efficiency or to reduce dependencies. The changes involve modifications to plotting functions, specifically in the `stan_plots.R` and `stan_plots_helpers.R` files. The overall goal is to improve the structure of the visualizations and its related functions.
r-packagebayesian-inferencestanrstanrstats
tidymodels/broom
Dec 2015 - Apr 2018
Convert statistical analysis objects from R into tidy format
Role in this project:Back-end Developer & Data Scientist
Back-end Developer & Data ScientistContributions:26 commits, 5 PRs, 9 comments in 2 years 4 months
Contributions summary:Jonah focused on enhancing the `broom` package's ability to tidy and present results from MCMC models. They introduced functionality to include Rhat and effective sample size estimates for `stanfit` objects, along with adding support for selecting specific parameters within these models. The changes involved modifying the `mcmc_tidiers.R` file to handle parameter selection, Rhat/ESS calculations, and fixing bugs related to parameter handling. The user's work also included the addition of examples demonstrating how to select parameters.
r-packagestatisticshypothesis-testingregression-modelstidymodels
Find and Hire Top DevelopersWe鈥檝e analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.