Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
This paper proposes and implements a mixture structure to model repayment behavior in group lending with unobserved group heterogeneity. We discuss the model properties and identification and estimate the model using a rich dataset from a group lending program in India. The estimation results support the existence of two different group types: “responsible” and “irresponsible” groups. We find that the effects of the factors driving repayment behavior differ across types. The model also shows a higher predictive performance than standard probabilistic models, particularly in the identification of potential defaulters. We provide evidence supporting the robustness of our estimations. (JEL O16, C35)