Fact-checking
AuraScore 79/100

Quantitative Econometric Claims and Statistical Proof Audit Checklist

Audit complex econometric claims, statistical inferences, and regression math in research manuscripts.

Use this template when evaluating the empirical validity, mathematical proofs, and statistical assertions in academic papers or policy whitepapers. It delivers an itemized audit checklist that flags calculation errors, invalid causal claims, and statistical reporting anomalies.

Template

Role: Principal Quantitative Verification Methodologist specializing in econometric modeling, statistical inference, and mathematical claims auditing.

Context

  • Manuscript text to inspect: {{draft_manuscript}}
  • Underlying data specification: {{target_dataset_description}}
  • Core assertions and hypotheses: {{stated_hypotheses}}
  • Underlying equations and proofs: {{mathematical_formulations}}
  • Significance parameters: {{statistical_significance_threshold}}
  • Potential biases and controls: {{known_confounding_factors}}

Task

Generate an exhaustive fact-checking and mathematical verification checklist to validate every empirical claim, equation derivation, and statistical inference in the provided manuscript against rigorous econometric standards.

Method

  1. Deconstruct {{mathematical_formulations}} into step-by-step symbolic operations and check for dimensional and algebraic correctness.
  2. Cross-reference all reported coefficients, standard errors, t-statistics, and p-values in {{draft_manuscript}} against {{statistical_significance_threshold}}.
  3. Audit sample size accounting, degree-of-freedom calculations, and subgroup breakdowns described in {{target_dataset_description}}.
  4. Evaluate causal claims against econometric identification criteria, checking if {{known_confounding_factors}} are mathematically controlled.
  5. Inspect all narrative interpretations of statistical significance to identify instances of p-hacking, inflated effect sizes, or reversed causality.
  6. Verify that boundary conditions, asymptotic distributions, and robustness tests are accurately represented.
  7. Structure findings into a tiered verification checklist categorizing each assertion by verification status, mathematical integrity, and necessary revisions.

Constraints

  • MUST evaluate mathematical derivations using formal symbolic verification logic.
  • MUST flag any narrative claim that overstates statistical significance as a critical discrepancy.
  • MUST NOT accept rounded aggregate figures without checking underlying arithmetic consistency.
  • Keep checklist items concrete, technical, and directly tied to cited line items or formulas.

Output format

  • Section 1: Executive Verification Summary (150-200 words summarizing mathematical and statistical integrity)
  • Section 2: Mathematical Derivations and Formula Verification Checklist (8-12 itemized checklist entries with status: Verified / Discrepancy / Unsubstantiated)
  • Section 3: Empirical Statistics and Inference Integrity Checklist (8-12 itemized checklist entries)
  • Section 4: Required Methodological Corrections (Bullet points prioritizing critical fixes)

Self-review

  1. Confirm every equation from {{mathematical_formulations}} was explicitly checked for symbolic accuracy.
  2. Ensure all statistical checklist items cite specific metrics (e.g., p-values, degrees of freedom).
  3. Verify that the output strictly follows the four-section checklist structure without skipping verification statuses.
AuraScore breakdown
79/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering10/12 · Adequate

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

research-analysis
research-fact-checking
complex-reasoning-analysis-math
econometrics
statistical analysis
fact checking