摘要：Development projects frequently use the strategy of group formation to promote project interventions such as producer groups and savings and lending groups. These groups are formed and encouraged by development projects for two primary reasons: 1) because the success of the intervention in some way relies on group participation and cooperation (e.g., savings and lending groups or sustainable management of a resource), or 2) because groups make it easier to disseminate the intervention and possibly improve its effectiveness via information sharing among participants. But for groups to be formed, high levels of trust and trustworthdiness among group members are considered a requirement. Implying that more trusting/trustworthy community members selfselect into forming these groups. However, it is also possible that the frequent interaction among group participants lead to higher levels of trust and cooperation. Then the question becomes whether group-based interventions take advantage of the social capital and social ties already existing in the communities or improves it. We apply the trust game to investigate whether farmers involved in group-based interventions promoted by a rural development project in Nicaragua, “Agriculture for Basic Needs” (A4N), reveal different levels of trust than farmers who were not exposed to the A4N group interventions. The A4N program, data and methods. The overarching strategy for the A4N project was to promote group organization and interaction, to build capacity in saving and lending, to introduce enhanced agricultural technologies, and provide technical assistance to farmers. As such, farmers in the A4N villages were invited and encouraged to form groups focused on one or more of the following project-supported objectives: saving and lending, learning sustainable agricultural technologies, and innovation and learning. We apply the trust game and survey questions to investigate whether farmers involved in group-based interventions promoted by A4N reveal different levels of trust than farmers who did not participate in the A4N group interventions. We explore these effects on trust levels among farmers in the same village. To achieve this objective, our experimental design involves two treatments that vary only in whether participants were involved in the A4N project or not. Specifically, we implement trust experiments in eight communities in Nicaragua – half of these communities where involved in the A4N project while the other half were not. Eight A4N and non-A4N villages were selected such that they had similar socio-economic characteristics, and selected A4N villages that had more than one A4N group with the goal of avoiding only having participants from a single group in a given session. A total of eight sessions – one session in each village – were conducted during May of 2012 with between 17 and 22 farmers participating in each session, for a total of 153 participants. For sessions in A4N villages, farmer-participants were recruited randomly from lists of farmers participating in groups promoted and supported by the A4N project. Similarly, for sessions in non-A4N villages, farmer-participants were chosen randomly from lists of farmers with similar demographic characteristics to the A4N farmers. This version of the trust game is a one-shot game, with no communication where all participants remain anonymous in that they do not know whom they are playing with. As in most trust games, participants are divided into two types – senders and receivers – and each sender is paired with one receiver. In addition, both senders and receivers are given equal initial endowments. The sender is then asked to decide what portion of their endowment they would like to send to the receiver. The sender can send all or none and knows that whatever portion they do not send they will get to keep. The sender – and receiver – also knows that the amount sent (or invested) is, in this case, tripled before it is given to the receiver. The receiver will now have their endowment plus three times what the sender sent. In the second step of the game, the receiver can return some amount of what they have (endowment plus three times what the sender sent) back to the sender. Discussion and results On average, A4N and non-A4N subjects do not differ in most socioeconomic characteristics, implying that both A4N and non-A4N participants were drawn from the same population. However, these two groups do differ in terms of gender, besides having invited a similar proportion of men and women to the meeting, more women participated in the A4N sections than men. The results suggest that A4N senders sent more than non-A4N senders, A4N sent 51% of their endowment, whereas non-A4N senders sent 46% (p-value=0.10 Mann-Whitney U test for equal means). However when we conduct multivariate analysis including socioeconomic characteristics, the difference becomes not statistically significant. In particular, the variable for gender (male=1) is negative and statistically significant, suggesting that women are more trusting than men. The results also suggest that they are there were not difference in trustworthiness. A4N receivers returned 32% of their available resources, and non-A4N receivers returned 35% (p-value=0.30 Mann-Whitney U test for equal means). In the multivariate analysis the proportion returned is explained by the amount sent, socioeconomic characteristics were not statistically significant. This results contrast with other studies that have found that subjects in a group are more trusting. Indicating that not necessarily more trusting individuals self-select to participate in groups. Particularly in the case of a rural development project is possible that the motivation of obtaining project benefits encouraged group formation. However it is also possible that group formation encourages trust and social capital formation, and further research on this should be carried out.
