Error-prone humans — role?
Cause of mistakes in science
Self-correction myth — belief?
Science automatically corrects flawed findings
Retraction — purpose?
Withdraws invalid or problematic publication
Honest errors — can lead to?
Retractions or corrections without misconduct
Careless errors — examples?
Typos, copy-paste mistakes, code errors
Negligent errors — include?
Poor design, weak analysis, low power
Error detection — tools?
Statcheck, GRIM, anomaly checks
Statcheck — function?
Recalculates p-values from reported stats
Retraction Watch — role?
Tracks retractions and reasons
Statcheck inconsistencies — signs?
Mismatched p-values, signs, or means
Optimistic rounding — effect?
Can falsely suggest significance
GRIM test — purpose?
Checks if means match data granularity
Randomization check — evaluates?
Baseline plausibility under random assignment
Blinding check — ensures?
Researchers unaware of group assignments
Measurement practices — issues?
Questionable scales, ad hoc items, low validity
Statistical power — meaning?
Ability to detect true effects
Low power — consequence?
Misses real effects or exaggerates findings
Data anomalies — detection?
Constraints violations, implausible patterns
Teste tes connaissances avec un QCM de 18 questions sur Enhancing Scientific Self-Correction.
1. What does the myth of self-correcting science claim about false or flawed findings?
2. In the reported loss-of-confidence survey, what proportion of respondents had lost confidence in at least one finding?
Révisez le cours complet dans la fiche de révision de Enhancing Scientific Self-Correction.
Voir la fiche →Importe ton cours et l'IA génère des flashcards en 30 secondes.
Générateur de flashcards