The role of education in the production of health: an empirical analysis of smoking behavior.

We estimate the effect of education on smoking. Our estimation strategy "differences out" the impact of unobserved characteristics correlated with education by exploiting education differences between similarly selected groups 1 year apart in their life cycle. Individuals with a given age, education, and student status in the current and previous year are compared to their counterparts born 1 year later with the same age, education, and student status in the following and current year. We find that an additional year of education does not have a causal effect on smoking. Unobserved factors correlated with education entirely explain their cross-sectional relationship.