Back to Annual Meeting

Back to Annual Meeting

APHA Scientific Session and Event Listing

M. Maria Glymour, ScD, Department of Epidemiology, Columbia University, 722 West 168th Street, New York, NY 10032, 212-305-9412, mglymour@hsph.harvard.edu

Many studies have shown a statistical association between education and health outcomes among the elderly. Because of the possible influence of unmeasured confounders, it is unclear whether the education gradient in health reflects a causal relation. Instrumental variables (IV) analyses of natural experiments offer one approach to overcoming the problem of unmeasured confounding, although identifying convincing natural experiments is difficult. In this talk, I will introduce IV and present my results using state compulsory schooling laws as natural experiments to estimate the effect of educational attainment on old age cognition, self-rated health, disability, and mortality.

Learning Objectives: At the conclusion of the session, the participant (learner) in this session will be able to

• Understand instrumental variables analyses

Presenting author's disclosure statement:

Any relevant financial relationships? No