Abstract:
|
The Millennium Villages Project (MVP) was a ten-year, multi-sector, rural development project implemented in ten sub-Saharan African sites. We estimate the MVP's effect on a variety of development indicators. Causal inference for the MVP context presents many challenges: a nonrandomized design, limited baseline data for candidate control areas, and the assignment of treatment to only ten sites, limiting effective sample sizes. We carry out a matching procedure tailored to small samples and designed to facilitate communication with subject-matter experts. We fit a hierarchical Bayesian model that partially-pools across multiple sites and multiple outcomes to ameliorate the problem of "multiple comparisons", and compare to results from a classical analysis. Our model is fit in Stan, a state-of-the-art platform for statistical modeling.
|