Research map / Probabilistic and scientific modeling / Causal discovery
Regularized Estimation of High-dimensional Factor-Augmented Vector Autoregressive (FAVAR) Models
Jiahe Lin, George Michailidis
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase observations from 200 to 500 (C4 vs C3) | FAVAR estimator · Simulation C3/C4 (sub-exponential noise) | Err(F): 0.39 -> 0.27 | Improved |
| increase observations from 200 to 500 (C4 vs C3) | FAVAR estimator · Simulation C3/C4 (sub-exponential noise) | Err(Gamma): 0.27 -> 0.18 | Improved |
| enlarge system from A1 (q=100,p2=50) to A2 (q=200,p2=100) | FAVAR estimator · Simulation A1/A2 | Err(F): 0.56 -> 0.90 | Hurt |
| enlarge system from A1 to A2 | FAVAR estimator · Simulation A1/A2 | Err(A): 0.35 -> 0.46 | Hurt |
| denser factor-to-X transition blocks (A3 vs A2 style sparse A) | FAVAR estimator · Simulation A2/A3 | SEN(A): 0.98 -> 0.86 | Hurt |
| near-pervasive factor effect with p2=500 (A4 vs A3) | FAVAR estimator · Simulation A3/A4 | SEN(A): 0.86 -> 0.75 | Hurt |
| heavy-tailed t4 noise in VAR system (C1 vs A1) | FAVAR estimator · Simulation A1/C1 | Err(Gamma): 0.45 -> 0.47 | No clear effect |
| heavy-tailed t8 noise in VAR system (C2 vs B1) | FAVAR estimator · Simulation B1/C2 | Err(Gamma): 0.27 -> 0.27 | No clear effect |
| more lags and higher SNR 2 (B1 vs A3) | FAVAR estimator · Simulation A3/B1 | Err(Gamma): 0.57 -> 0.27 | Improved |
Closest papers by meaning
- High Dimensional Forecasting via Interpretable Vector Autoregression (JMLR 2020 · similarity 0.87)
- Regularized Estimation and Testing for High-Dimensional Multi-Block Vector-Autoregressive Models (JMLR 2017 · similarity 0.86)
- Estimating Structured Vector Autoregressive Models (ICML 2016 · similarity 0.85)
- Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators (ICLR 2024 · similarity 0.82)
- A Set-Sequence Model for Time Series (NeurIPS 2026 · similarity 0.82)
- An Analysis of Linear Time Series Forecasting Models (ICML 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
