Lessons From Quantile Panel Estimation of the Environmental Kuznets Curve

We employ quantile regression fixed effects models to estimate the income-pollution relationship on <italic>NO</italic> _{<italic>x</italic>} (nitrogen oxide) and <italic>SO</italic> ₂ (sulfur dioxide) using U.S. data. Conditional median results suggest that conditional mean methods provide too optimistic estimates about emissions reduction for <italic>NO</italic> _{<italic>x</italic>}, while the opposite is found for <italic>SO</italic> ₂. Deleting outlier states reverses the absence of a turning point for <italic>SO</italic> ₂ in the conditional mean model, while the conditional median model is robust to them. We also document the relationship's sensitivity to including additional covariates for <italic>NO</italic> _{<italic>x</italic>}, and undertake simulations to shed light on some estimation issues of the methods employed.