Many individuals have empathetic feelings towards animals but frequently consume meat. We investigate this "meat paradox" using insights from the literature on motivated reasoning in moral dilemmata. We develop a model where individuals form self-serving beliefs about the suffering of animals caused by meat consumption in order to alleviate the guilt associated with their dietary choices. The model predicts that the price of meat has a causal effect on individuals' beliefs: high prices foster realism by lowering the returns to self-deception, which magnify the price elasticity of meat consumption. The model also predicts a positive relationship between individuals' taste for meat and their propensity to engage in self-deception, a causal effect of aggregate consumption on individual beliefs, and the coexistence of equilibria of "collective realism" and "collective denial".

We show how incorporating Gilboa, Maccheroni, Marinacci, and Schmeidler's (2010) notion of objective rationality into the ↵-MEU model of choice under ambiguity (Hurwicz, 1951) can overcome several challenges faced by the baseline model without objective rationality. The decision-maker (DM) has a subjectively rational preference % ^, which captures the complete ranking over acts the DM expresses when forced to make a choice; in addition, we endow the DM with a (possibly incomplete) objectively rational preference % ⇤ , which captures the rankings the DM deems uncontroversial. Under the objectively founded ↵-MEU model, % ^has an ↵-MEU representation and % ⇤ has a unanimity representation à la Bewley (2002), where both representations feature the same utility index and set of beliefs. While the axiomatic foundations of the baseline ↵-MEU model are still not fully understood, we provide a simple characterization of its objectively founded counterpart. Moreover, in contrast with the baseline model, the model parameters are uniquely identified. Finally, we provide axiomatic foundations for prior-by-prior Bayesian updating of the objectively founded ↵-MEU model, while we show that, for the baseline model, standard updating rules can be ill-defined.