This paper analyzes the repayment rates of credit groups belonging to three group-based credit programs in Bangladesh: the Association for Social Advancement (ASA), the Bangladesh Rural Advancement Committee (BRAC), and the Rangpur Dinajpur Rural Service (RDRS). Hypotheses are drawn from economic theory relating group responsibility, and the resulting monitoring by peers, to a more effective enforcement of contractual obligations as well as to improved ability of the group as a whole to repay loans. Specific tests are performed on the following hypothesized determinants: group size, size of loans, degree of loan rationing, enterprise mix within groups, demographic characteristics, social ties and status, and occurrence of idiosyncratic shocks. Analysis is conducted using TOBIT maximum likelihood procedures. Implications for policy and institutional design are discussed.