This paper presents semiparametric estimators of distributional impacts of interventions (treatment) when selection to the program is based on observable characteristics. Distributional impacts of a treatment are calculated as differences in inequality measures of the potential outcomes of...

We propose a method of retrospective counterfactual imputation in panel data settings with later-treated and always-treated units, but no never-treated units. We use the observed outcomes to impute the counterfactual outcomes of the later-treated using a matrix completion estimator. We propose a...

Proximity augments homeless students' educational outcomes. Homeless K-8 graders whose families are placed in shelters near their schools have 8 percent (2.4 days) better attendance, are a third (18 percentage points) less likely to change schools, and exhibit higher rates of proficiency and...

Using an original administrative dataset in the context of a scarcity induced-natural experi-ment in New York City, I find that families placed in shelters in their neighborhoods of origin remain there considerably longer than those assigned to distant shelters. Locally-placed families also...

Centralized school assignment algorithms must distinguish between applicants with the same preferences and priorities. This is done with randomly assigned lottery numbers, nonlottery tie-breakers like test scores, or both. The New York City public high school match illustrates the latter, using...

We place young professionals into established firms to shadow middle managers. Using random assignment into program participation, we find positive average effects on wage employment, but no average effect on the likelihood of self-employment. We match individuals to firms using a...

The economics 'credibility revolution' has promoted the identification of causal relationships using difference-in-differences (DID), instrumental variables (IV), randomized control trials (RCT) and regression discontinuity design (RDD) methods. The extent to which a reader should trust claims...

This chapter describes the main impact evaluation methods, both experimental and quasi-experimental, and the statistical model underlying them. Some of the most important methodological advances to have recently been put forward in this field of research are presented. We focus not only on the...

Binary treatments are often ex-post aggregates of multiple treatments or can be disaggregated into multiple treatment versions. Thus, effects can be heterogeneous due to either effect or treatment heterogeneity. We propose a decomposition method that uncovers masked heterogeneity, avoids...

This paper discusses pairing double/debiased machine learning (DDML) with stacking, a model averaging method for combining multiple candidate learners, to estimate structural parameters. We introduce two new stacking approaches for DDML: short-stacking exploits the cross-fitting step of DDML to...