Statistical Test Results for Model Performance Comparison

5.5 KB of significance test results for validating performance differences across models, authored by Dan Jiang and last updated in April 2026. The data is stored in an XLS file and is licensed for reuse under CC-BY-4.0. Its small size suggests it likely contains the outputs of multiple statistical tests rather than the raw model data.

Use Cases

• Validate significant performance differences between machine learning models based on reported test results.
• Assess the consistency of model evaluation outcomes across multiple statistical tests.
• Support methodological rigor in academic papers or reports by providing statistical evidence for model comparisons.

Strengths

• Provides a focused collection of statistical test results for model comparison.
• Released under the permissive CC-BY-4.0 license, allowing for broad reuse and sharing.

Limitations

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

Provenance

Source

figshare

Collection Method

Likely compiled from the outputs of statistical analysis software.

Time Range

null

Freshness

Last updated 2026-04-21 17:32:58; freshness should be verified.

Geography

null