Liberal Arts and Sciences
Karmakar Lab
Led by Sayar Karmakar · Statistics
What we study
The Karmakar Lab studies statistical methods for time series, high-dimensional data, and forecasting. They use computational approaches to analyze and model complex datasets.
What working here is like
- Computational
- No organisms (data only)
- Coding required
- Projects
- 2
- Papers
- 5
Current projects
Time series and forecasting
Statistical methods for data collected over time, including volatility forecasting.
Spatial and high-dimensional data
Methods for finding anomalies and estimating models in large, spatially linked data sets.
Summaries are written by AI in plain language from public symposium abstracts and may be imperfect.
Recent papers, explained
- Generalized percolation games on the two-dimensional square lattice and ergodicity of associated probabilistic cellular automata
2026 · Advances in Applied Probability
Studies a generalized model of percolation games on a 2D grid.
- A bootstrap test for testing the equality of two ultra-high dimensional covariance matrices
2026 · Journal of Multivariate Analysis
Show 3 more papersShow fewer
- Spillover and predictability of volatility of 50 major cryptocurrencies: Evidence from a LASSO-regularized Quantile VAR
2026 · The North American Journal of Economics and Finance
- Machine learning forecasting of U.S. stock market volatility: The role of stock and oil bubbles
2026 · Research in International Business and Finance
Tests if stock and oil bubbles improve stock market volatility forecasts.
- Return‐Volatility Nexus in the Digital Asset Class: A Dynamic Multilayer Connectedness Analysis
2025 · Bulletin of Economic Research
Analyzes connections between returns and volatility in digital assets.
Plain-language summaries are AI-written and reviewed by us; check the paper for details.
How to reach out
Sayar Karmakar hasn't set up this page yet. Their UF Scholars profile lists their publications.