ROSE: Robust Sliced Inverse Regression for Heavy-Tailed High-Dimensional Data

13.3 MB of data and code supporting the ROSE method for robust sliced inverse regression. The dataset, authored by Jing Zeng and last updated in May 2026, likely contains simulation results and empirical studies demonstrating a novel statistical method for handling predictors with heavy-tailed distributions in high-dimensional settings.

Use Cases

• Benchmarking robust dimension reduction methods based on the described ROSE algorithm
• Studying the performance of SIR variants on heavy-tailed data as mentioned in the description
• Comparing computational efficiency of robust methods that do not require extra tuning parameters

Strengths

• Dataset is 13.3 MB in size, indicating a manageable download
• License is CC-BY-4.0, permitting open sharing and adaptation
• Includes multiple file formats (e.g., CSV, R, ZIP) suggesting diverse components

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• Description metadata is limited; actual data quality requires manual inspection after download

Provenance

Source

figshare

Freshness

Last updated 2026-05-18 14:19:55; freshness should be verified