We propose the concept of survey rationalizability, that we base on classical item response theories in psychology. Survey rationalizability involves positioning survey questions on a common scale such that, in the case of attitude (respectively, aptitude) surveys, each respondent gives higher support to questions that are more aligned with her views (respectively, less difficult). We first demonstrate that ideas from standard revealed preference analysis can be used to characterize when deterministic responses on dichotomous surveys are rationalizable. We then show that these results readily extend to polytomous questions and stochastic responses. Furthermore, we investigate the identification of the models.

For further information please contact: erika.somma@unibocconi.it