While potentially negative impacts of credit constraints on economic development have long been discussed conceptually, empirical evidence for Africa remains limited. We use a direct elicitation approach on a national sample of Rwandan rural households to empirically assess the extent and nature of credit rationing in the semi-formal sector and its impact, using an endogenous switching model. Elimination of all constraints could increase output by some 17 per cent. Implications for policy and research are spelled out.