Measuring peer effects on youth smoking behaviour

This paper examines the role of peer effects in teenagers' smoking behaviour in the U.S.A. I present a random utility model that incorporates complementarity between individual and peer smoking. A Markov process model of smoking interactions between individuals is presented. I estimate the structural parameters of the model using a steady-state distribution that is determined by the Markov process. The empirical results strongly support the presence of positive peer effects. Interestingly, peer interactions are found to be stronger within the same gender than across genders. The same result is found for race. Moreover, a multiplier effect is found.