Using an alternative to classical statistics, this paper reanalyzes results from three published studies of interventions to increase employment and reduce welfare dependency. The analysis formally incorporates prior beliefs about the interventions, characterizing the results in terms of the distribution of possible effects, and generally confirms the earlier published findings.
Publications
Helping Low-Income and First-Generation Students Make Good College Choices

Too many low-income, college-ready students are “undermatching” — enrolling in colleges for which they are academically overqualified or not going to college at all. Early results from the College Match Program in three Chicago high schools suggest that it’s possible to help students navigate the complicated college application process and make more informed decisions.
An Introduction to the Performance-Based Scholarship Demonstration in California
One of six sites in MDRC’s national demonstration, California’s program, run in partnership with Cash for College, is testing performance-based scholarships of differing amounts and durations that supplement existing aid and that students can use at any accredited postsecondary institution.

A rigorous study that takes advantage of lottery-like features in New York City’s high school admissions process demonstrates that new small public high schools that are open to students of all academic backgrounds have substantial impacts on rates of graduation with Regents diplomas for every disadvantaged subgroup of students that was examined.
In some experimental evaluations of classroom- or school-level interventions, random assignment is conducted at the student level and the program is delivered at the higher level. This paper clarifies the correct causal interpretation of “program impacts” when this study design is used and discusses the implications and limitations of this research design. A real example is used to demonstrate the paper’s key points.
Seven-Year Findings from the Jobs-Plus Demonstration

An extended analysis of Jobs-Plus, an ambitious employment program inside some of the nation’s poorest inner-city public housing developments, finds substantial effects on residents’ earnings a full three years after the program ended.