The goal of the proposed research is to complete the work begun under our previous grant on the determinants and consequences of high school completion via GED certification and to understand the causes and consequences of secondary school drop out decisions. We seek support to complete our ongoing analysis of the data sets, to extend our analysis to additional data sets, and to synthesize and organize all of the available evidence in a coherence framework. We have developed a number of tentative hypotheses regarding the GED and we seek support to test them in a rigorous fashion using additional data sets and different identifying assumptions on our current data sets. We seek support to examine the quality of the GED as a signal of both scholastic and social skills. Our goal is a monograph on the causes and consequences of dropping out of high school and of GED attainment. We also seek support to complete the task of constructing rigorously justified econometric models for analyzing life cycle dynamics that are more general than the standard grade transition models currently used. We are currently developing a rich class of semiparametric models for analyzing transitions among life cycle or life course states that are not dependent on arbitrary distributional assumptions and that can be used to conduct rigorous counterfactual policy simulations to evaluate the effectiveness of various interventions in the life cycle of youth such as the GED. We seek support to expand the set of tools used to identify policy counterfactuals under a variety of plausible behavioral assumptions and to use these tools to analyze GED recipiency.
| Carneiro, Pedro; Heckman, James J; Vytlacil, Edward (2010) Evaluating Marginal Policy Changes and the Average Effect of Treatment for Individuals at the Margin. Econometrica 78:377-394 |
| Heckman, J J; Vytlacil, E J (1999) Local instrumental variables and latent variable models for identifying and bounding treatment effects. Proc Natl Acad Sci U S A 96:4730-4 |
