Ethnic markers and the emergence of group-specific norms: an experiment

Abstract

Visible markers are an important factor in social interactions. Some researchers have argued that one of their roles is to promote cooperation, but models designed to address this issue have yielded contradictory results. Here we present an experimental study of the effect of visible markers on the emergence of social norms where human subjects play a binary coordination game. Our results do not show different, marker-dependent behaviors. Instead, in practically all sessions participants achieved a global equilibrium disregarding the markers. Our findings suggest that simple markers may have a limited role in promoting the emergence of group-dependent social norms and call for further research investigating the role of markers in more sophisticated social settings.

Figure 1

Experimental profiles of coordination rates for the transient(rounds 0 to 40); X-axis: coordination rate within the subpopulation that shared the same marker as the individual; Y-axis: coordination rate within the subpopulation that shares the complementary marker. Coloured, the marker of the participants.

Figure 2

Experimental profiles of coordination rates for the transient (rounds 0 to 40); X-axis: coordination rate within the subpopulation that shared the most popular action in the population; Y-axis: coordination rate within the subpopulation that shares the complementary action. Coloured, the marker of the participants.

Figure 3

Coordination with agents with same and different marker for different e and group size. Groups are characterized by four different configurations according to these parameters: $\{N,e\}=\{\{10,0.5\},\{10,1\},\{20,0.5\},\{20,1\}\}$.

Figure 4

K-Means clustering for the groups that have a size of $N=10$ participants. The separation confirms that the space of parameters of coordination rate separates the groups.

Figure 5

(a) Distribution of the difference between the valuation of the outcomes. (b) Distribution of the temporal differences between the different times participants were asked about their valuation.

Figure 6

Relation between the binary coordination game and the degree of norm compliance (measured from 0 to 20). On the X axis, the degree of norm compliance; on the Y axis, the number of coordinations for a player during the game.

Figure 7

(a) Coordination rate distribution for the different populations with $N=10$ for the rounds (0, 40). (b) Coordination rate distribution for the different populations with $N=20$ for the rounds (0, 40).

Figure 8

(a) Coordination rate distribution for the sum of the populations with $N=10$ for the rounds (0, 40). (b) Coordination rate distribution for the sum of the populations with $N=20$ for the rounds (0, 40).

Figure 9

Experimental profiles of trust distributions for the four different configurations, depending on the parameters N,e.