Cross-Sectional Impact Analysis: Bias from Dropouts

Abstract

Several microfinance organizations have begun using a management tool, developed by Assessing the Impact of Microenterprise Services (AIMS) at the United States Agency for International Development (USAID), to assess impact. This tool recommends comparing veteran members to new members of a microcredit program, and attributes any difference to the impact of the program. The tool introduces a potential source of bias into estimates of impact by not instructing organizations to include program dropouts in their calculations. This paper uses data from a longitudinal study in Peru of Mibanco borrowers and non-borrowers to quantify some, but not all, of the biases in the cross-sectional approach. In these data, not including dropouts overestimates the impact of the credit program. Furthermore, we find that the sample composition shifted over the two years, introducing further bias into a cross-sectional impact assessment. The "reestimates" here do not produce an unbiased estimate of impact, but are calculated merely to assess the attrition and sample composition biases in the cross-sectional approach that compares veterans to new entrants.

Why are Informal Loans Still a Big Deal? Evidence from North-east Thailand

“…Regardless of what method is used, the primary issue that must be taken into account is that programme placement might not be exogenous and/or participation in those programmes might not be exogenous (Coleman, 1999). As a consequence, the effect of these programmes might be due to unobservable determinants (Karlan & Tedeschi, 2010).…”

A Comprehensive Review of Microfinance Impacts, Sustainability and Outreach

“…Microfinance increases individual and household income; it allows holistic development by increasing the income of the household [35]. Empirical studies in Peru [36,37] report positive impacts of microfinance programs on household income, but the amount of income drops-though, still positive-when considering dropout bias. Similarly in Zambia, profit estimates by DID method is positive but significantly lower than that of dropout bias [38].…”