Kevin Sheppard
Senior Researcher - Economist at Keble College
London, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolKevin Sheppard is a senior researcher and economist with 14+ years of experience at the intersection of academia and applied financial econometrics, holding tenured positions at the University of Oxford and a senior research role at the U.S. Office of Financial Research. He specializes in volatility and correlation measurement and modeling, teaching these topics while consulting on practical implementations for financial institutions and regulators. A hands-on contributor to major scientific Python libraries (statsmodels, NumPy, SciPy, pandas and related projects), he improves statistical accuracy and robustness through bug fixes, performance work, and extensive test-driven development. His background in both rigorous theory (PhD in Economics, UC San Diego) and low-level code contributions (including C/Python fixes in NumPy) gives him a rare ability to bridge mathematical foundations and production-ready software. Colleagues rely on him for careful validation of time-series methods and for translating advanced econometric techniques into reliable, well-tested tools.
14 years of coding experience
University of California, San DiegoBS, Mathematics, BS, Mathematics at The University of Texas at Austin
Stackoverflow
2,735reputation
524kreached
75answers
1question
pandas
top-5%
regression
top-5%
python
top-5%
Github Skills (45)
unit-testing10
algorithms10
debug10
scipy10
pytest10
python10
testing10
pandas10
statistics10
time-series10
statistic10
numpy10
typehinting10
statistical-models10
fileio10
Programming languages (12)
Github contributions (5)
bashtage/arch
Jul 2014 - Nov 2022
ARCH models in Python
Role in this project:
Backend Developer & Test Automation Engineer
Backend Developer & Test Automation EngineerContributions:52 releases, 1 review, 1068 commits in 8 years 5 months
Contributions summary:Kevin appears to be primarily involved in improving the test coverage and the general quality of the code base. Their commits demonstrate a focus on test-driven development, including the addition of unit tests for various components. The user's contributions focus on test coverage of regression models by adding new functionality to the tests.
forecastingpythonriskrisk-analysisfinancial-econometrics
bashtage/linearmodels
Jun 2016 - Nov 2022
Additional linear models including instrumental variable and panel data models that are missing from statsmodels.
Role in this project:Back-end Developer
Back-end DeveloperContributions:51 releases, 2 reviews, 1031 commits in 6 years 5 months
Contributions summary:Kevin implemented enhancements to the interface for weight integration and formula support for panel models. These changes primarily involved modifying the model class in the core package to include support for weights within the panel models and to introduce initial formula support. These changes added the ability to add weights to the estimation and perform the computation, and provided a new method that facilitated the specification of the model using a formula instead of only passing arrays.
first-differencelinear-modelsgmmdata-modelsseemingly-unrelated-regression
Find and Hire Top DevelopersWe’ve 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.