A Threshold Autoregressive Asymmetric Stochastic Volatility Strategy to Alert of Violations of the Air Quality Standards

Montero Lorenzo, J.M.; Sánchez-Ollero, J.L.; Fernandez-Aviles, G.

doi:10.22059/ijer.2010.287

A Threshold Autoregressive Asymmetric Stochastic Volatility Strategy to Alert of Violations of the Air Quality Standards

Authors

J.M. Montero Lorenzo ¹

J.L. Sánchez-Ollero ²

G. Fernandez-Aviles ¹

¹ Facultad de Ciencias Jurídicas y Sociales de Toledo, University of Castilla-La Mancha Cobertizo San Pedro Mártir s/n, 45071, Toledo, Spain

² María Carmen García-Centeno, Facultad de Ciências Econômicas y Empresariales, Julián Romea 23, 28003, Madrid, Spain

10.22059/ijer.2010.287

Abstract

Air quality is a topic of crucial importance, because air pollution is one of the most important pollution problems in the world. In particular, predicting or detecting a future extreme air pollution episode or predicting the violation of an air quality standard, is of crucial interest in the field of pollution control. There have been a variety of attempts to reach this purpose both from the perspective of the extreme value theory and the time series analysis, but as far as we know there is none successful strategy to alert of violations of the standards. This is why in this article we propose a new strategy, a threshold autoregressive asymmetric stochastic volatility strategy to alert of an immediate violation of the particulate matter quality standards, which take into account the different answer of the volatility to a positive or negative, but equal in magnitude, relative variation of the level of the pollutant in the previous period. Particulate matter is one of the still uncontrolled pollutants in big cities. This novel approach has been applied in Madrid City (Spain), the thirdmost populous municipality in the European Union, and it is able to predict a great percentage of violations of the standard.

Keywords

Pollution

Particulate matter

Air quality violation

Volatility

environment

TA-ARSV model

Functional