Meta-Analytic Synthesis and Evidence Dashboard Review Checklist
Evaluate systematic review and meta-analytic evidence synthesis dashboards for bias, heterogeneity, and visual accuracy.
Deploy this checklist when building or auditing research synthesis dashboards that pool multi-study evidence. It ensures correct forest plot parameters, subgroup stratification accuracy, and transparent bias reporting.
Role: Senior Research Synthesis Director specializing in systematic reviews, evidence aggregation, and interactive meta-analysis visualization.
Context
- Corpus boundary: {{evidence_corpus_scope}}
- Heterogeneity indicators: {{heterogeneity_metrics}}
- Primary effect metrics: {{primary_effect_sizes}}
- Stratification dimensions: {{subgroup_stratification_factors}}
- Visualization components: {{visual_encoding_specifications}}
- Quality governance standard: {{peer_review_standards}}
Task
Produce an evidence synthesis quality assurance checklist to review and certify an interactive research synthesis dashboard displaying pooled evidence from {{evidence_corpus_scope}}, ensuring strict compliance with {{peer_review_standards}}.
Method
- Define intake verification checkpoints for study eligibility, weights, and extraction fidelity within {{evidence_corpus_scope}}.
- Detail algorithmic verification items for fixed-effect and random-effects pooling models calculating {{primary_effect_sizes}}.
- Create mathematical verification steps for evaluating between-study variance using {{heterogeneity_metrics}}.
- Draft checklist items auditing interactive forest plots and funnel plots defined in {{visual_encoding_specifications}}.
- Formulate validation items for cross-sectional filtering and subgroup slicing against {{subgroup_stratification_factors}}.
- Specify bias assessment checks, including publication bias heuristics and sensitivity analysis switches.
- Detail compliance verification steps mapped directly to {{peer_review_standards}} guidelines.
Constraints
- MUST structure all items as actionable, imperative checklist statements.
- MUST NOT allow summary metrics to display without accompanied uncertainty intervals.
- Forest plot verifications MUST mandate display of individual study weights and confidence intervals.
- Subgroup analyses must contain minimum sample size warnings to prevent spurious post-hoc findings.
Output format
- Section 1: Study Extraction & Data Provenance Verification (4-5 binary checks)
- Section 2: Statistical Pooling & Heterogeneity Checks (5-7 mathematical verification items)
- Section 3: Graphical Encoding & Visual Robustness Checks (5-6 visual audit items)
- Section 4: Subgroup & Sensitivity Analysis Integrity (4-5 interaction items)
- Section 5: Standards Compliance Checklist (3-4 alignment verification items)
Self-review
- Ensure all variables are referenced and contextualized within the review steps.
- Confirm clear distinction between random-effects and fixed-effect evaluation logic.
- Verify that each section contains specific pass/fail evaluation criteria.
Explicit role, a named task, and discrete steps the model can follow.
Background, inputs and variables the model needs before it starts.
Hard boundaries — what the model must and must not do.
A named, field-level shape for the response.
Ordered work items that force analysis before an answer.
Length and structure that travel across frontier models.
Signal density — instruction weight without padding.
Documented variables so the scaffold adapts to new inputs.
Quality bar, assumptions and behaviour when inputs are thin.
How much real usage the template has behind it.