Establish a preregistered minimum effect size for falsification

Establish a defensible preregistered smallest effect of interest $r_{\min}>0$ for the cross-domain signed-obstruction correlation, thereby specifying when an observed near-zero association can reject the shared-mechanism account.

Background

The theory predicts a positive cross-domain association, but an observed estimate near zero cannot by itself exclude arbitrarily small positive effects. The paper therefore requires a quantitative threshold rather than a merely directional prediction.

The simulations use a 30% shared-score-variance alternative for power calculations, but the authors emphasize that this is a detectable alternative rather than an effect size theoretically entailed by the account. The minimum effect size needed for a genuinely falsifiable preregistered test remains unspecified.

References

This paper does not yet fix $r_{\min$:} the $30\%$ of-score-variance shared component used in the power simulations below is an alternative the design can detect, which is a different thing from an effect the theory commits to, and promoting one to the other is an author decision the preregistration must record before data collection.

— Binding-Motivated Contextuality: A Cross-Domain Cyclic Test in Perception and Judgment  (2609.23977 - Shavit, 21 Sep 2026) in Section 3, subsection “Falsifier --- and it needs a number, not a direction”