randomization devices that are equivalent under the Reduction Axiom. Instead choice behavior is consistent with subjective …

, information acquisition is not solicited, and afterwards randomly. The key insight is that randomization makes precontractual …

randomization plans are almost always compromised. Multiple hypotheses are frequently tested. "Significant" effects are often … that the planned randomization protocol was implemented. In fact, as in many social experiments, the intended randomization … protocol was compromised. Accounting for compromised randomization, multiple-hypothesis testing, and small sample sizes, we …