Benjamin Boniece
Drexel University, PA·Mathematics & Statistics
Stock market crashes, bursts of social media activity after news events and sudden changes in animal migration share a pattern. A system that seemed stable abruptly shifts.
- Fields
Mathematics & Statistics
Social Science
- Topics
statistics
time series analysis
high-frequency data
- Grants
- 1 known grant, through Jun 2027
What they work on
- Develop methods to detect shocks that affect many series in high-dimensional, high-frequency data, possibly asynchronously, using time-localized principal component analysis in factor-structured models.
- Build testing frameworks based on time-localized bootstrapping to quantify how strongly a shock affects an entire system of time-dependent variables.
- Estimate jump behavior in multivariate high-frequency models and develop time-localized clustering methods to group series by their behavior around shock events.
More about the research
Statisticians call these events shocks. Detecting them reliably helps scientists understand large systems of linked variables and manage risk. When many variables are recorded at very high frequency, as in financial markets, climate records or statistical physics, fine-timescale data can reveal hidden connections. It can also show uncertainty shared across the whole system.
Why it matters
More reliable detection of systemic shocks in high-frequency data could help analysts in finance, econometrics, climatology and other empirical sciences spot abrupt system-wide changes, measure how widely they spread and better manage risk and uncertainty in large interconnected systems.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Ting Zhang
University of Georgia, GA·Mathematics & Statistics
Develop change-point tests that stay powerful when the post-change signal varies unpredictably, using a causal representation framework and Gaussian approximation to set statistically sound alarm thresholds.
Yao Zheng
University of Connecticut, CT·Mathematics & Statistics·Early-career
Develop recurrent neural network (RNN) models for high-dimensional time series that stay interpretable through Granger causality, a test of whether one series predicts another, to balance accuracy and interpretability.
Alexander Aue
University of California-Davis, CA·Mathematics & Statistics
Derive new probability results describing the structure of nonlinear, possibly heavy-tailed functional time series, where each observation is an entire curve.
The school
Drexel University: 11 labs on PI Pages, $170M a year on research, 282 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.