This article investigates whether individual responses on Catalan independence are congruent with what would be expected according to his or her profile. Previous research has pointed out that responses to this question are affected by different biases, especially by the social desirability bias and the spiral of silence bias. Therefore, individuals choose an answer that would not have been the chosen answer in other social or political circumstances. This lack of congruence between observed individual responses and predicted responses are analysed by predicting each respondent answer through multiple imputation. This `blind' imputation allows for controlling individuals' uncertainty and for comparing observed and predicted results. Findings show that lack of congruence especially affects those that choose ``No", ``Abstention" or are undecided but there are not systematic evidences that hiding prefereces bias the ``Yes" results. Conclusions of this paper are important in order to understand and analyse how indecision operates in surveys.