Upcoming Events at Wellesley:
The Quantitative Analysis Institute presents a lecture by
Donald B. Rubin
John L. Loeb Professor of Statistics, Harvard University
Thursday, April 17, 4:15 pm
Clapp Library Lecture Room
Title: Evaluating the Effect of Training on Wages in the Presence of Noncompliance, Nonemployment, and Missing Data
The effects of a job training program, Job Corps, on both employment and wages are evaluated using data from a randomized study. Principal stratiﬁcation is used to address, simultaneously, the complications of noncompliance, wages that are only partially deﬁned because of nonemployment, and unintended missing outcomes. The ﬁrst two complications are of substantive interest, whereas the third is a nuisance. The objective is to ﬁnd a parsimonious model that can be used to inform public policy. We conduct a likelihood-based analysis using ﬁnite mixture models estimated by the expectation-maximization (EM) algorithm. We maintain an exclusion restriction assumption for the effect of assignment on employment and wages for noncompliers, but not on missingness. We provide estimates under the “missing at random” assumption, and assess the robustness of our results to deviations from it. The plausibility of meaningful restrictions is investigated by means of scaled log-likelihood ratio statistics. Substantive conclusions include the following. For compliers, the effect on employment is negative in the short term; it becomes positive in the long term, but these effects are small at best. For always employed compliers, that is, compliers who are employed whether trained or not trained, positive effects on wages are found at all time periods. Our analysis reveals that background characteristics of individuals differ markedly across the principal strata. We found evidence that the program should have been better targeted, in the sense of being designed differently for different groups of people, and speciﬁc suggestions are offered. Previous analyses of this dataset, which did not address all complications in a principled manner, led to less nuanced conclusions about Job Corps. This is joint work with Paolo Frumento, Fabrizia Mealli, and Barbara Pacini.
The QAI provides workshops for both students and faculty. Please be in touch with requests for events aimed at a particular audience.
Courses: Many courses touch on quantitative topics. The QAI can develop and present workshops targeted at students in a particular course, focused on how statistics or data analysis relates to the course material.
Faculty: We are organizing a periodic work-in-progress seminar for faculty engaged in quantitative research, as well as short courses on the statistical software R. Please get in touch if you'd like to join.
Student Interest Groups: Workshops are available for students focused on particular career goals (medicine, law, journalism) or who want to understand the statistics underlying a particular area.
Guests: The QAI organizes short courses and guest lecturers from visiting scholars.
Past Events at Wellesley:
Math Department Colloquium, Wed, Nov 6
One Embryo or Two for In Vitro Fertilization? Assessing causation without randomization
Economics Department Brown Bag Lunch Seminar, Thu, Oct 31
A Potential Outcomes, and Typically More Powerful, Alternative to "Cochran-Mantel-Haenszel"
Pforzheimer Learning and Teaching Center Talk, Mon, Oct 21
Quantitative Analysis in the Classroom: Statistics workshops targeted at your course