Dr. Giancarlo Visconti (Assistant Professor of Political Science) will offer a workshop on Recent Advances in Optimal matching at 3 pm, Friday (April 15th), BRNG 1284.
The workshop will provide a new perspective on survey research. Please join if you are interested.
A common problem encountered in observational studies is limited overlap in covariate distributions across treatment groups. To address this problem, and avoid strong modeling assumptions, it has become common practice to restrict analyses to the portions of the treatment groups that overlap or, ultimately, are balanced in their covariate distributions.
Often, this is done by matching the estimated propensity score or coarsened versions of the observed covariates. A recent alternative methodology that, in a sense, encompasses these two approaches is cardinality matching. Cardinality matching offers the researcher better control over the research process.
We discuss how this method can be extended to build matched samples that are not only balanced but also representative of a target population by design. We also show how this method enhances sensitivity analyses for hidden biases. We explain these advancements through an observational study of the electoral impact of the 2010 earthquake in Chile.