Random assignment is insufficient for measured treatment responses to recover causal effects (comparative statics) in dynamic economies. We characterize analytically bias probabilities and magnitudes. If the policy variable is binary there is attenuation bias. With more than two policy states,...

The empirical effectiveness of economic policies that operate theoretically through similar channels differs substantially. We document this fact by comparing an easy-to-grasp expectations-based policy, unconventional fiscal policy, with a policy whose implications are harder to understand by...