In 2010, a magnitude 8.8 earthquake hit Chile, devastating parts of the country. Having just completed its national socioeconomic survey (CASEN), Chile interviewed a subsample of respondents, creating unusual longitudinal data about the same individuals before and after a major disaster. The follow-up evaluated posttraumatic stress symptoms (PTSS) using Davidson’s Trauma Scale. We use these data with two goals in mind. Most studies of PTSS following disasters rely on recall to characterize the state of affairs prior to the disaster. In contrast, we use the CASEN to study effects of the earthquake on PTSS with prospective data on pre-exposure conditions, free of recall bias. Second, we illustrate recent developments in statistical methodology for the design and analysis of observational studies. In particular, we use new and recent methods for multivariate matching to control 46 covariates that describe demographics, housing quality, wealth, health and health insurance prior to the earthquake. Also, we use the statistical theory of design sensitivity to select a study design whose findings are expected to be insensitive to small or moderate biases from failure to control some unmeasured covariate. We find that posttraumatic stress symptoms were dramatically but unevenly elevated among residents of strongly shaken areas of Chile when compared to similar individuals in largely untouched parts of the country. In 96% of exposed-control pairs exhibiting substantial PTSS, the exposed individual experienced elevated symptoms (95% CI:[0.91,1.00]).
José is a PhD student in statistics at The Wharton School of the University of Pennsylvania. His main research interest is causal inference with applications to medical and social science. More information about his work can be found at http://www-stat.wharton.upenn.edu/~josezubi/.