Exercise and Adolescent Mental Health: New Evidence from Longitudinal Data

Background: Recent U.S. government recommendations state that increased physical activity can substantially improve adolescent psychological well-being. However, many of the studies upon which this conclusion is based did not adequately address the role of difficult-to-measure factors that could be correlated with both physical activity and adolescent mental health. Aim of the Study: The primary aim of this study is to estimate the effect of physical activity on adolescent psychological well-being controlling for the influence of unmeasured school- and individual-level confounding factors. Methodology: Drawing on data from the first two waves of the National Longitudinal Study of Adolescent Health, we use ordinary least squares to estimate the effect of physical activity and hours of inactivity on two psychometrically sound measures of psychological well-being (the Center for Epidemiologic Studies Depression scale and the Rosenberg Self-Esteem scale). Next, we add school fixed effects and then individual fixed effects to the estimating equation in order to control for difficult-to-measure factors that could be correlated with both physical activity and adolescent mental health. Results: Ordinary least squares (OLS) estimates show that a higher frequency of moderate or physical exercise is associated with improved psychological well-being for adolescents. This result is robust to the inclusion of school fixed effects, but when we control for fixed individual heterogeneity by first-differencing the data, the estimated effects of physical activity on depression and self-esteem decline sharply, often becoming small in magnitude or statistically indistinguishable from zero. We conclude that OLS estimates of the effect of physical activity on emotional health may be biased upwards. Limitations: While the nationally representative panel data we use is a rich source of information on mental health, our measure of physical activity is limited in that it fails to capture total time spent exercising. Moreover, while our statistical approach controls for time-invariant unobservables, we cannot rule out the possibility of time-varying unobserved confounders. Implications: Although policy interventions designed to promote more exercise among youths may have important physical health benefits, our findings suggest that the short-run emotional benefits are likely small and concentrated at higher frequencies of physical activity. Future Research: To enhance the internal validity of research in this area, future work could tackle the difficult challenge of identifying exogenous variation in physical exercise using a natural experiment approach.