Testing unilateral and bilateral link formation

We propose a test of whether self-reported network data is best seen as an actual link or willingness to link and, in the latter case, whether this link is generated by an unilateral or bilateral link formation process. We illustrate this test using survey answers to a risk-sharing question in an African village. We find that bilateral link formation fits the data better than unilateral link formation, but the data are best interpreted as willingness to link rather than an actual link. We then expand the model to include self-censoring and find it to fit the data significantly better than willingness to link. This suggests that, in our data, the data generating process behind self-reported links is a hybrid between an actual link and willingness to link.