Anonymity versus privacy in the dictator game: revealing donor decisions to recipients does not substantially impact donor behavior

Abstract

Anonymity is often offered in economic experiments in order to eliminate observer effects and induce behavior that would be exhibited under private circumstances. However, anonymity differs from privacy in that interactants are only unaware of each others' identities, while having full knowledge of each others' actions. Such situations are rare outside the laboratory and anonymity might not meet the requirements of some participants to psychologically engage as if their actions were private. In order to explore the impact of a lack of privacy on prosocial behaviors, I expand on a study reported in Dana et al. (2006) in which recipients were left unaware of the Dictator Game and given donations as "bonuses" to their show-up fees for other tasks. In the current study, I explore whether differences between a private Dictator Game (sensu Dana et al. (2006)) and a standard anonymous one are due to a desire by dictators to avoid shame or to pursue prestige. Participants of a Dictator Game were randomly assigned to one of four categories-one in which the recipient knew of (1) any donation by an anonymous donor (including zero donations), (2) nothing at all, (3) only zero donations, and (4) and only non-zero donations. The results suggest that a lack of privacy increases the shame that selfish-acting participants experience, but that removing such a cost has only minimal effects on actual behavior.

Figure 1. Distribution of Dictator donations across the four conditions.