domains / families / research / jebo-robustness

jebo-robustness

separate

Use when a Journal of Economic Behavior & Organization (JEBO) result may be fragile to demand effects, multiple comparisons, specification, or tuning. Organizes robustness by the behavioral threat each check addresses — for experiments, observational designs, and simulations; it does not redesign the identification or write the prose.

When to use

• Experiments with multiple treatment arms or outcomes
• Observational results sensitive to controls or estimator choice
• Agent-based results sensitive to grid, seed, or tuning
• Unstructured robustness appendices
• Mechanism robustness checks
• Multiple comparisons correction
• Demand effects and order effects
• Specification curve and multiverse analysis

When not to use

• Redesigning identification
• Writing prose

Skill page

Source