Illusory correlations, like the belief that a full moon affects behavior, persist through confirmation bias despite having no basis in evidence¶

Claim · All claims
Evidence · 1 study · quant-synthesis r? · q4 · n=aggregated across ~40 studies
Currency · newest study 1985 · not yet checked against its sources · not reviewed by a person · overdue for a recheck since 1990: baselines and conditions change

People can perceive a relationship between two variables that does not actually exist — an illusory correlation — and go on believing it even when the underlying rate of the supposedly-related behavior is constant.

Subclaims¶

q4 i? A meta-analysis of nearly 40 studies found no relationship between lunar phase and human behavior, contradicting the widespread popular belief that behavior becomes stranger during a full moon. → Rotton & Kelly 1985

Evidence¶

Rotton & Kelly 1985¶

Rotton, J., & Kelly, I. W. (1985). Much ado about the full moon: A meta-analysis of lunar-lunacy research. Psychological Bulletin, 97(2), 286-306. https://doi.org/10.1037/0033-2909.97.2.286

q4 · meta-analysis of nearly 40 prior studies · i? · no source text available to check; the entry prints no effect size · n=aggregated across ~40 studies · quant-synthesis · r?

Rotton and Kelly pooled the results of nearly 40 published studies that had tested whether measures of human behavior (crime rates, psychiatric admissions, calls to crisis lines, and similar records) varied with the phase of the moon. The pooled result found no reliable relationship between lunar phase and any of these behavioral measures. The popular belief persists anyway: people notice unusual behavior that happens to occur during a full moon and remember it, while failing to notice that unusual behavior occurs at essentially the same rate during every other phase of the lunar cycle — the noticing itself is not random, even though the underlying behavior is.

Discussion¶

This is a specific, well-documented case of a more general vulnerability described in Evidence-Based Teaching and Scientific Reasoning: confirmation bias leads people to notice and remember confirming instances of a belief while the (much larger) set of disconfirming instances goes unnoticed. The consequence is not merely a harmless folk belief — Fiedler (2004) notes that illusory correlations of this kind are implicated in the formation of prejudicial attitudes toward particular groups, where a few salient, remembered instances of a stereotyped behavior get mistaken for a genuine group-level pattern.

Related Claims¶

• The RCT is considered the gold standard of research evidence because randomization ensures only the intervention could cause treatment-control outcome differences — the general claim this finding bears on, with the studies behind it
• Teacher effectiveness compounds over consecutive years — an example of a correlational finding with strong enough design (tracked cohorts, contrasted assignment patterns) to support a causal-adjacent policy conclusion, unlike an illusory correlation
• Builders' perceived control, satisfaction, and perceived quality show no detectable association with their measured visual atypicality, so convergence goes unnoticed from the inside — a narrower finding that bears on this claim
• A CCSR research review concludes that four academic mindsets (belonging, growth beliefs, self-efficacy and value) increase perseverance and improve academic behaviors — related