Bounded Rationality and Limited Datasets: Testable Implications, Identification, and Out-of-Sample Prediction

Theories of bounded rationality are typically characterized over an exhaustive data set. How does one tell whether observed choices are consistent with a theory if the data is incomplete? How can out-of-sample predictions be made? What can be identified about preferences? This paper aims to operationalize some leading bounded rationality theories when the available data is limited, as is the case in most practical settings. We also point out that the recent bounded rationality literature has overlooked a methodological pitfall that can lead to ‘false positives’ and ‘empty’ out-of-sample predictions when testing choice theories with limited data.