Asymmetry and Incomplete Information in an Experimental Volunteer's Dilemma

The Volunteer's Dilemma is a provision point version of the classic public goods game where, once the level is obtained, all n players enjoy the benefit of the public good. Each member faces a binary set of options including a costly decision to volunteer and a costless no volunteer choice. The volunteer's dilemma is a unique version in that only one volunteer is needed to supply the public good. Typical examples of the volunteer's dilemma range from helping potential victims of violent crime to political vetoes, where volunteering comes at a real cost, monetary or otherwise. Following prior studies, the situation is modeled as n members of a group receiving a monetary payoff of V if at least one player volunteers at a cost of C. In the event of a no-volunteer outcome, members receive a lower payoff of L. Since V > L, the preferred outcome for any player is to not volunteer while at least one other group member volunteers. However, it is assumed that C < V-L, which makes volunteering at cost C better than a no-volunteer outcome for every individual player. The trade-off between costly volunteering and the benefit to free-riding while possibly receiving L is the dilemma. Our experimental design features 10 sessions testing cost asymmetry in the volunteer's dilemma, with complete and incomplete information, across group sizes of N = 2 and N = 6, funded by the Russell Sage Foundation. Prior studies (e. g. Diekmann, 1985) have produced theoretical predictions and tested staged field experiments (Darley and Latane, 1968), while the experimental literature remains undeveloped. Most recently, Goeree et. al. (2005) explored the relationship between group size and volunteering, where the Nash equilibrium predicts the probability of volunteering to be a decreasing function of group size, while the probability of a no-volunteer outcome is increasing in the number of players. Testing group sizes N=2, 3, 6, 9, and 12, the authors find evidence to support the former hypothesis but not the latter. Our study tests a variation of the volunteer's dilemma where the cost to volunteer is not symmetric across members of a group. Diekmann (1993) gives an example of three bystanders observing a victim in danger of drowning. If only one of the bystanders is able to swim, such that C(k)< C(i), it seems apparent that the bystander who can swim should save the victim. However the Nash solution implies that the non-swimmers are expected to save the victim. We find that increasing the cost to volunteer significantly decreases the rate of volunteering. We are also able to show that the rate of volunteering is positively correlated with other group members' costs, which suggests that people tend to take their turn volunteering when their cost to volunteer is relatively low.