satisficing and stochastic choice

with victor aguiar and Mark Dean - JET(2016)

Satisficing is a hugely influential model of boundedly rational choice, yet it cannot be easily tested using standard choice data. We develop necessary and sufficient conditions for stochastic choice data to be consistent with satisficing, assuming that preferences are fixed, but search order may change randomly. The model predicts that stochastic choice can only occur amongst elements that are always chosen, while all other choices must be consistent with standard utility maximization. Adding the assumption that the probability distribution over search orders is the same for all choice sets makes the satisficing model a subset of the class of random utility models.

working papers


This paper provides a novel predictive approach to power for revealed preference testing. In finite samples conditions may be so undemanding that is impossible to detect violations. The likelihood of false positives depends on the precision to which underlying preferences are identified; the more precise the identification the smaller deviations need to be in order to be detected. This paper approaches the degree of identification by its behavioral manifestation: the precision of the predictions that can be constructed given the (partially) identified preferences. The proposed measure also accounts for the effect of the pattern of observed choices on the probability of finding such violations; and can naturally be extended to reflect the severity of the violations if observed choices are inconsistent with the theory. This approach allows to differentiate among designs that seem to have similar standard power, and its power adjustment does not vanish in moderate sample sizes.


 Revealed preference restrictions provide testable implications for many theories of consumption behavior. Often, empirical evidence finds violations to these conditions which raises the question of how severe they are. The severity of the violations does not only depend on the extent of the observed deviations, but also on the sensitivity of the test to detect them. This paper provides a joint treatment for the severity of the violations and the sensitivity of the test in discrete choice environments by assessing the amount of information about preferences that can be inferred from data while allowing for errors. The proposed approach allows to compare across (limited) data sets and different models of behavior, addressing the concern raised by De Clippel and Rozen (2014) about extensibility of bounded rationality models.

aggregate random consideration sets: theory and evidence

with victor aguiar


"the impact of confidence on risk taking behavior and performance"

with nicholas coleman

work in progress