High Noon for Microfinance Impact Evaluations: Re-investigating the Evidence from Bangladesh
重新分析了Pitt和Khandker的小额信贷数据，通过倾向得分匹配和敏感性分析发现，小额信贷的影响因借款人性别而异，且结果易受不可观测因素的选择性偏差影响，因此因果关系不明确。
Abstract Recently, microfinance has come under increasing criticism raising questions of the validity of iconic studies which have justified it, such as Pitt and Khandker. Chemin applied propensity score matching to the Pitt and Khandker data, finding different impacts, but does not disaggregate by gender of borrower. We first replicate Chemin and extend his analysis in two ways. We test the robustness of propensity score matching results to selection on unobservables using sensitivity analysis, and we investigate propensity score matching estimates of impacts by gender of borrowers. The mainly insignificant impacts of microfinance differ greatly by gender of borrower, but are all vulnerable to selection on unobservables. We are therefore not convinced that the relationships between microfinance and outcomes are causal with these data.