U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

Understanding the Impact of Career Academy Attendance: An Application of the Principal Stratification Framework for Causal Effects Accounting for Partial Compliance

NCJ Number
253750
Journal
Evaluation Review Volume: 36 Issue: 2 Dated: 2012 Pages: 99-132
Author(s)
Lindsay Page
Date Published
2012
Length
34 pages
Annotation

Since results from MDRC's longitudinal, random-assignment evaluation of career-academy high schools revealed that several years after high-school completion, those randomized to receive the academy opportunity realized a $175 (11 percent) increase in monthly earnings, on average, the current study examined the impact of duration of actual academy enrollment, because nearly half of treatment group students either never enrolled or participated for only a portion of high school.

Abstract

Based on data from the experimental evaluation, the current study used a principal stratification framework and Bayesian inference to investigate the causal impact of academy participation. The analysis focused on a sample of 1,306 students across seven sites in the MDRC evaluation. Participation was measured by number of years of academy enrollment, and the outcome of interest was average monthly earnings in the period of four to eight years after high school graduation. The study estimated an average causal effect of treatment assignment on subsequent monthly earnings of approximately $588 among males who remained enrolled in an academy throughout high school and more modest impacts among those who participated only partially. Different from an instrumental variables approach to treatment non-compliance, which allows for the estimation of linear returns to treatment take-up, the more general framework of principal stratification allows for the consideration of non-linear returns, although at the expense of additional model-based assumptions. (publisher abstract modified)