Is There Unit Root in the Nitrogen Oxides Emissions: A Monte Carlo Investigation?

Abstract

Use of the time‐series econometric techniques to investigate issues about environmental regulation requires knowing whether air pollution emissions are trend stationary or difference stationary. It has been shown that results regarding trend stationarity of the pollution data are sensitive to the methods used. I conduct a Monte Carlo experiment to study the size and power of two unit root tests that allow for a structural change in the trend at a known time using the data‐generating process calibrated to the actual pollution series. I find that finite sample properties of the Perron test are better than the Park and Sung Phillips‐Perron (PP) type test. Severe size distortions in the Park and Sung PP type test can explain the rejection of a unit root in air pollution emissions reported in some environmental regulation analyses.

Evaluating the Impact of Environmental Policy on the Trend Behavior of Us Emissions of Nitrogen Oxides and Volatile Organic Compounds

“…The difference in the results can be explained by the use of different tests. In particular, Jones [] shows that the Park and Sung PP test exhibits substantial size distortion (false rejections of the unit root null hypothesis) for processes calibrated to match the dynamics of the pollution data when there is only one break at the time the CAAA of 1970 were passed.…”