A Group-Based Approach to Causal Analysis Using Longitudinal Data with Applications to Gang Membership and Teen Violence

• Activity Number: 499
• Type: Contributed
• Date/Time: Thursday, August 10, 2006 : 8:30 AM to 10:20 AM
• Sponsor: Social Statistics Section
• Author(s): Amelia Haviland*+ and Daniel Nagin and Paul Rosenbaum
• Companies: RAND Corporation and Carnegie Mellon University and University of Pennsylvania
• Keywords: trajectory groups ; mixture models ; propensity score ; optimal matching ; covariance adjustment ; observational study

Abstract

Using data from the Montréal Study of Boys, the effects on subsequent violence of joining a gang at age 14 are studied controlling for characteristics of boys prior to age 14. The boys are divided into trajectory groups based on violence from ages 11 to 13, and within trajectory groups, joiners are optimally matched to a variable number of controls using propensity scores, Mahalanobis distances, and a combinatorial optimization algorithm. The trajectory groups define meaningful subpopulations where effects may be different, while propensity scores and optimal matching tend to balance twelve baseline covariates. By using between 1 and 7 controls for each joiner, greater efficiency is obtained than by pair matching, with greater bias reduction than is available by matching in a fixed ratio. We develop new efficiency bounds to guide decisions about the structure of the matching.