Core Capabilities

The seven capability areas in full: methodology critique, bias detection, statistical analysis evaluation, evidence quality assessment, logical fallacy identification, research design guidance, and claim evaluation — each with the questions to ask and what the answers imply.

Use review_sources.md for current framework versions and primary sources. Keep missing reporting, risk of bias, applicability, and certainty distinct.

Core Capabilities

1. Methodology Critique

Evaluate research methodology for rigor, validity, and potential flaws.

Apply when:

• Reviewing research papers
• Assessing experimental designs
• Evaluating study protocols
• Planning new research

Evaluation framework:

1. Study Design Assessment
2. Is the design appropriate for the research question?
3. Can the design support causal claims being made?
4. Are comparison groups appropriate and adequate?
5. Consider whether experimental, quasi-experimental, or observational design is justified

1. Validity Analysis
2. Internal validity: Can we trust the causal inference?
3. Check randomization quality
4. Evaluate confounding control
5. Assess selection bias
6. Review attrition/dropout patterns
7. External validity: Do results generalize?
8. Evaluate sample representativeness
9. Consider ecological validity of setting
10. Assess whether conditions match target application
11. Construct validity: Do measures capture intended constructs?
12. Review measurement validation
13. Check operational definitions
14. Assess whether measures are direct or proxy
15. Statistical conclusion validity: Are statistical inferences sound?
16. Verify adequate power/sample size
17. Check assumption compliance
18. Evaluate test appropriateness

1. Control and Blinding
2. Was randomization properly implemented (sequence generation, allocation concealment)?
3. Was blinding feasible and implemented (participants, providers, assessors)?
4. Are control conditions appropriate (placebo, active control, no treatment)?
5. Could performance or detection bias affect results?

1. Measurement Quality
2. Are instruments validated and reliable?
3. Are measures objective when possible, or subjective with acknowledged limitations?
4. Is outcome assessment standardized?
5. Are multiple measures used to triangulate findings?

Reference: See references/scientific_method.md for detailed principles and references/experimental_design.md for comprehensive design checklist.

2. Bias Detection

Identify and evaluate potential sources of bias that could distort findings.

Apply when:

• Reviewing published research
• Designing new studies
• Interpreting conflicting evidence
• Assessing research quality

Systematic bias review:

1. Cognitive Biases (Researcher)
2. Confirmation bias: Are only supporting findings highlighted?
3. HARKing: Were hypotheses stated a priori or formed after seeing results?
4. Publication bias: Are negative results missing from literature?
5. Cherry-picking: Is evidence selectively reported?
6. Check for preregistration and analysis plan transparency

1. Selection Biases
2. Sampling bias: Is sample representative of target population?
3. Volunteer bias: Do participants self-select in systematic ways?
4. Attrition bias: Is dropout differential between groups?
5. Survivorship bias: Are only "survivors" visible in sample?
6. Examine participant flow diagrams and compare baseline characteristics

1. Measurement Biases
2. Observer bias: Could expectations influence observations?
3. Recall bias: Are retrospective reports systematically inaccurate?
4. Social desirability: Are responses biased toward acceptability?
5. Instrument bias: Do measurement tools systematically err?
6. Evaluate blinding, validation, and measurement objectivity

1. Analysis Biases
2. P-hacking: Were multiple analyses conducted until significance emerged?
3. Outcome switching: Were non-significant outcomes replaced with significant ones?
4. Selective reporting: Are all planned analyses reported?
5. Subgroup fishing: Were subgroup analyses conducted without correction?
6. Check for study registration and compare to published outcomes

1. Confounding
2. What variables could affect both exposure and outcome?
3. Were confounders measured and controlled (statistically or by design)?
4. Could unmeasured confounding explain findings?
5. Are there plausible alternative explanations?

Reference: See references/common_biases.md for comprehensive bias taxonomy with detection and mitigation strategies.

3. Statistical Analysis Evaluation

Critically assess statistical methods, interpretation, and reporting.

Apply when:

• Reviewing quantitative research
• Evaluating data-driven claims
• Assessing clinical trial results
• Reviewing meta-analyses

Statistical review checklist:

1. Sample Size and Power
2. Was a priori power analysis conducted?
3. Is sample adequate for detecting meaningful effects?
4. Is the study underpowered (common problem)?
5. Do significant results from small samples raise flags for inflated effect sizes?

1. Statistical Tests
2. Are tests appropriate for data type and distribution?
3. Were test assumptions checked and met?
4. Are parametric tests justified, or should non-parametric alternatives be used?
5. Is the analysis matched to study design (e.g., paired vs. independent)?
6. Is n the number of independent units rather than technical replicates or time points?

1. Multiple Comparisons
2. Were multiple hypotheses tested?
3. Was correction applied (Bonferroni, FDR, other)?
4. Are primary outcomes distinguished from secondary/exploratory?
5. Could findings be false positives from multiple testing?

1. P-Value Interpretation
2. Are p-values interpreted as test-statistic tail probabilities under the null model and analysis procedure, rather than hypothesis probabilities?
3. Is non-significance incorrectly interpreted as "no effect"?
4. Is statistical significance conflated with practical importance?
5. Are exact p-values reported, or only "p < .05"?
6. Is there suspicious clustering just below .05?

1. Effect Sizes and Confidence Intervals
2. Are effect sizes reported alongside significance?
3. Are confidence intervals provided to show precision?
4. Is the effect size meaningful in practical terms?
5. Are standardized effect sizes interpreted with field-specific context?

1. Missing Data
2. How much data is missing?
3. Is missing data mechanism considered (MCAR, MAR, MNAR)?
4. How is missing data handled (deletion, imputation, maximum likelihood)?
5. Could missing data bias results?

1. Regression and Modeling
2. Is the model overfitted (too many predictors, no cross-validation)?
3. Are predictions made outside the data range (extrapolation)?
4. Are multicollinearity issues addressed?
5. Are model assumptions checked?
6. Does the model identify the claimed parameter, or do rank deficiencies, symmetries, flat profiles, constraints, or prior sensitivity leave it unresolved despite good fit?

1. Common Pitfalls
2. Correlation treated as causation
3. Ignoring regression to the mean
4. Base rate neglect
5. Texas sharpshooter fallacy (pattern finding in noise)
6. Simpson's paradox (confounding by subgroups)

Reference: See references/statistical_pitfalls.md for detailed pitfalls and correct practices.

4. Evidence Quality Assessment

Evaluate the strength and quality of evidence systematically.

Apply when:

• Weighing evidence for decisions
• Conducting literature reviews
• Comparing conflicting findings
• Determining confidence in conclusions

Evidence evaluation framework:

1. Study Design Hierarchy
2. Systematic reviews/meta-analyses (synthesize the certainty of their underlying evidence)
3. Randomized controlled trials
4. Cohort studies
5. Case-control studies
6. Cross-sectional studies
7. Case series/reports
8. Expert opinion (lowest)

Important: This is an intervention-oriented shorthand, not a universal ranking. Match the design to the question; a review does not become high certainty by pooling.

1. Quality Within Design Type
2. Result-specific risk of bias: RoB 2 for randomized intervention results, ROBINS-I for non-randomized intervention effects, QUADAS-3 for diagnostic accuracy estimates; record the exact version and use the matching scope
3. Methodological rigor
4. Transparency and reporting completeness
5. Conflicts of interest

1. GRADE Considerations (if applicable)
2. Define the outcome/comparison and GRADE application. For intervention evidence, specify traditional design-based or ROBINS-I-integrated starting certainty; avoid double-counting non-randomization (see references/evidence_hierarchy.md).
3. Downgrade for:
4. Risk of bias
5. Inconsistency across studies
6. Indirectness (wrong population/intervention/outcome)
7. Imprecision (wide confidence intervals, small samples)
8. Publication bias
9. Upgrade for:
10. Justified large effects, dose response, or plausible confounding opposing the observed effect under the applicable GRADE approach; not automatic bonuses

1. Convergence of Evidence
2. Stronger when:
3. Multiple independent replications
4. Different research groups and settings
5. Different methodologies converge on same conclusion
6. Mechanistic and empirical evidence align
7. Weaker when:
8. Single study or research group
9. Contradictory findings in literature
10. Publication bias evident
11. No replication attempts

1. Contextual Factors
2. Biological/theoretical plausibility
3. Consistency with established knowledge
4. Temporality (cause precedes effect)
5. Specificity of relationship
6. Strength of association

Reference: See references/evidence_hierarchy.md for detailed hierarchy, GRADE system, and quality assessment tools.

5. Logical Fallacy Identification

Detect and name logical errors in scientific arguments and claims.

Apply when:

• Evaluating scientific claims
• Reviewing discussion/conclusion sections
• Assessing popular science communication
• Identifying flawed reasoning

Common fallacies in science:

1. Causation Fallacies
2. Post hoc ergo propter hoc: "B followed A, so A caused B"
3. Correlation = causation: Confusing association with causality
4. Reverse causation: Mistaking cause for effect
5. Single cause fallacy: Attributing complex outcomes to one factor

1. Generalization Fallacies
2. Hasty generalization: Broad conclusions from small samples
3. Anecdotal fallacy: Personal stories as proof
4. Cherry-picking: Selecting only supporting evidence
5. Ecological fallacy: Group patterns applied to individuals

1. Authority and Source Fallacies
2. Appeal to authority: "Expert said it, so it's true" (without evidence)
3. Ad hominem: Attacking person, not argument
4. Genetic fallacy: Judging by origin, not merits
5. Appeal to nature: "Natural = good/safe"

1. Statistical Fallacies
2. Base rate neglect: Ignoring prior probability
3. Texas sharpshooter: Finding patterns in random data
4. Multiple comparisons: Not correcting for multiple tests
5. Prosecutor's fallacy: Confusing P(E|H) with P(H|E)

1. Structural Fallacies
2. False dichotomy: "Either A or B" when more options exist
3. Moving goalposts: Changing evidence standards after they're met
4. Begging the question: Circular reasoning
5. Straw man: Misrepresenting arguments to attack them

1. Science-Specific Fallacies
2. Galileo gambit: "They laughed at Galileo, so my fringe idea is correct"
3. Argument from ignorance: "Not proven false, so true"
4. Nirvana fallacy: Rejecting imperfect solutions
5. Unfalsifiability: Making untestable claims

When identifying fallacies:

• Name the specific fallacy
• Explain why the reasoning is flawed
• Identify what evidence would be needed for valid inference
• Note that fallacious reasoning doesn't prove the conclusion false—just that this argument doesn't support it

Reference: See references/logical_fallacies.md for comprehensive fallacy catalog with examples and detection strategies.

6. Research Design Guidance

Provide constructive guidance for planning rigorous studies.

Apply when:

• Helping design new experiments
• Planning research projects
• Reviewing research proposals
• Improving study protocols

Design process:

1. Research Question Refinement
2. Ensure question is specific, answerable, and falsifiable
3. Verify it addresses a gap or contradiction in literature
4. Confirm feasibility (resources, ethics, time)
5. Define variables operationally

1. Design Selection
2. Match design and identification assumptions to descriptive, predictive, or causal question
3. Consider feasibility and ethical constraints
4. Choose between-subjects, within-subjects, or mixed designs
5. Plan factorial designs if testing multiple factors

1. Bias Minimization Strategy
2. Implement randomization when possible
3. Plan blinding at all feasible levels (participants, providers, assessors)
4. Identify and plan to control confounds (randomization, matching, stratification, statistical adjustment)
5. Standardize all procedures
6. Plan to minimize attrition

1. Sample Planning
2. Conduct a priori power analysis (specify expected effect, desired power, alpha)
3. Account for attrition in sample size
4. Define clear inclusion/exclusion criteria
5. Consider recruitment strategy and feasibility
6. Plan for sample representativeness

1. Measurement Strategy
2. Select validated, reliable instruments
3. Use objective measures when possible
4. Plan multiple measures of key constructs (triangulation)
5. Ensure measures are sensitive to expected changes
6. Establish inter-rater reliability procedures

1. Analysis Planning
2. Prespecify all hypotheses and analyses
3. Designate primary outcome clearly
4. Plan statistical tests with assumption checks
5. Specify how missing data will be handled
6. Plan to report effect sizes and confidence intervals
7. Consider multiple comparison corrections

1. Transparency and Rigor
2. Preregister study and analysis plan
3. Use reporting guidelines (CONSORT 2025/SPIRIT 2025, STROBE, PRISMA 2020 as applicable)
4. Plan to report all outcomes, not just significant ones
5. Distinguish confirmatory from exploratory analyses
6. Commit to data/code sharing

Reference: See references/experimental_design.md for comprehensive design checklist covering all stages from question to dissemination.

7. Claim Evaluation

Systematically evaluate scientific claims for validity and support.

Apply when:

• Assessing conclusions in papers
• Evaluating media reports of research
• Reviewing abstract or introduction claims
• Checking if data support conclusions

Claim evaluation process:

1. Identify the Claim
2. What exactly is being claimed?
3. Is it a causal claim, associational claim, or descriptive claim?
4. How strong is the claim (proven, likely, suggested, possible)?

1. Assess the Evidence
2. What evidence is provided?
3. Is evidence direct or indirect?
4. Is evidence sufficient for the strength of claim?
5. Are alternative explanations ruled out?

1. Check Logical Connection
2. Do conclusions follow from the data?
3. Are there logical leaps?
4. Is correlational data used to support causal claims?
5. Are limitations acknowledged?

1. Evaluate Proportionality
2. Is confidence proportional to evidence strength?
3. Are hedging words used appropriately?
4. Are limitations downplayed?
5. Is speculation clearly labeled?

1. Check for Overgeneralization
2. Do claims extend beyond the sample studied?
3. Are population restrictions acknowledged?
4. Is context-dependence recognized?
5. Are caveats about generalization included?

1. Red Flags
2. Causal language without an explicit estimand and defensible identifying assumptions
3. "Proves" or absolute certainty
4. Cherry-picked citations
5. Ignoring contradictory evidence
6. Dismissing limitations
7. Extrapolation beyond data

Provide specific feedback:

• Quote the problematic claim
• Explain what evidence would be needed to support it
• Suggest appropriate hedging language if warranted
• Distinguish between data (what was found) and interpretation (what it means)