Lessons from Quantile Panel Estimation of the Environmental Kuznets Curve

The environmental Kuznets curve (EKC) hypothesizes that the income-pollution rela- tionship has an inverted U shape: pollution increases with income up to a turning point beyond which it decreases. The empirical literature has concentrated on estimation of this relationship at the mean employing longitudinal data, with the typical ?nding supporting the inverted U shape. Conditional mean estimation, however, can mask heterogeneities present at higher and/or lower quantiles of the emissions?distribution, in addition to being more sensitive to the presence of outliers. We apply methods for conditional-quantile panel ?xed e¤ects models to the estimation of the income-pollution relationship on U.S. state-level data on NOx (nitrogen oxide) and SO2 (sulfur dioxide) pollutants over the period 1929- 1994. Our results indicate that conditional mean methods provide too optimistic estimates about emissions reduction of NOx, as conditional-quantile methods suggest that the turning point of the relationship occurs at higher values of income; while the opposite is found for SO2. Another important lesson drawn is that the income-pollution relationship is sensitive to the presence of outliers in the data.