significance-verdict

Automating regression significance checks involves evaluating p-values against thresholds like 0.05 and assessing effect sizes for economic significance. This skill automates this dual verdict process, consuming baseline regression outputs to determine if results meet both statistical and practical significance criteria.

Economic significance in regression analysis determines if the effect size of your results is practically meaningful, beyond just being statistically significant. You need to evaluate it when making research decisions to ensure your findings have real-world impact rather than just mathematical validity.

Applying human-in-the-loop decision processes for practical significance involves automating statistical checks while requiring manual review of economic impact. This skill enforces p-value requirements automatically but supports human-in-the-loop input to evaluate whether effect sizes are economically meaningful for your specific research context.

Integrating regression verdict outputs into a research workflow is supported through the full_research_workflow Steps 7-8. This skill consumes baseline regression results and iteration logs to generate verdict assessments, writing the final evaluation to verdict/stage_1_baseline_verdict.md for downstream workflow consumption.

Limitations of automating regression verdicts include rigid p-value thresholds like < 0.05 and the inability to automatically judge context-specific economic significance. This skill requires human-in-the-loop input for economic significance evaluation and depends on properly structured baseline regression inputs and interpretation boundaries.