IDEAS home Printed from
   My bibliography  Save this paper

A Dynamic Multiple Equation Approach for Forecasting PM2.5 Pollution in Santiago, Chile


  • Stella Moisan

    (Universidad de Talca, Chile)

  • Rodrigo Herrera

    (Universidad de Talca, Chile)

  • Adam Clements

    () (QUT)


A methodology based on a system of dynamic multiple linear equations is proposed that incorporates hourly, daily and annual seasonal characteristics to predict hourly pm2.5 pollution concentrations for 11 meteorological stations in Santiago, Chile. It is demonstrated that the proposed model has the potential to match or even surpass the accuracy of other linear and nonlinear forecasting models in terms of fit and predictive ability. In addition, the model is successful in predicting various categories of high concentration events, up to 76% of mid-range and 100% of extreme-range events as an average across all stations. This forecasting model is considered a useful tool for government authorities to anticipate critical episodes of air quality so as to avoid the detrimental impacts economic and health impacts of extreme pollution levels.

Suggested Citation

  • Stella Moisan & Rodrigo Herrera & Adam Clements, 2017. "A Dynamic Multiple Equation Approach for Forecasting PM2.5 Pollution in Santiago, Chile," NCER Working Paper Series 117, National Centre for Econometric Research.
  • Handle: RePEc:qut:auncer:2017_01

    Download full text from publisher

    File URL:
    Download Restriction: no

    Other versions of this item:

    References listed on IDEAS

    1. Bohringer, Christoph & Jochem, Patrick E.P., 2007. "Measuring the immeasurable -- A survey of sustainability indices," Ecological Economics, Elsevier, vol. 63(1), pages 1-8, June.
    2. Raffaella Giacomini & Halbert White, 2006. "Tests of Conditional Predictive Ability," Econometrica, Econometric Society, vol. 74(6), pages 1545-1578, November.
    3. Diebold, Francis X & Mariano, Roberto S, 2002. "Comparing Predictive Accuracy," Journal of Business & Economic Statistics, American Statistical Association, vol. 20(1), pages 134-144, January.
    4. Sujit K. Sahu & Kanti V. Mardia, 2005. "A Bayesian kriged Kalman model for short‐term forecasting of air pollution levels," Journal of the Royal Statistical Society Series C, Royal Statistical Society, vol. 54(1), pages 223-244, January.
    5. Amisano, Gianni & Giacomini, Raffaella, 2007. "Comparing Density Forecasts via Weighted Likelihood Ratio Tests," Journal of Business & Economic Statistics, American Statistical Association, vol. 25, pages 177-190, April.
    6. Clements, A.E. & Hurn, A.S. & Li, Z., 2016. "Forecasting day-ahead electricity load using a multiple equation time series approach," European Journal of Operational Research, Elsevier, vol. 251(2), pages 522-530.
    7. Tilmann Gneiting & Roopesh Ranjan, 2011. "Comparing Density Forecasts Using Threshold- and Quantile-Weighted Scoring Rules," Journal of Business & Economic Statistics, Taylor & Francis Journals, vol. 29(3), pages 411-422, July.
    8. R. Winkler & Javier Muñoz & José Cervera & José Bernardo & Gail Blattenberger & Joseph Kadane & Dennis Lindley & Allan Murphy & Robert Oliver & David Ríos-Insua, 1996. "Scoring rules and the evaluation of probabilities," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 5(1), pages 1-60, June.
    9. Tim Hill & Marcus O'Connor & William Remus, 1996. "Neural Network Models for Time Series Forecasts," Management Science, INFORMS, vol. 42(7), pages 1082-1092, July.
    10. Gneiting, Tilmann & Ranjan, Roopesh, 2011. "Comparing Density Forecasts Using Threshold- and Quantile-Weighted Scoring Rules," Journal of Business & Economic Statistics, American Statistical Association, vol. 29(3), pages 411-422.
    11. Franses, Philip Hans & Draisma, Gerrit, 1997. "Recognizing changing seasonal patterns using artificial neural networks," Journal of Econometrics, Elsevier, vol. 81(1), pages 273-280, November.
    12. Zaiyong Tang & Paul A. Fishwick, 1993. "Feedforward Neural Nets as Models for Time Series Forecasting," INFORMS Journal on Computing, INFORMS, vol. 5(4), pages 374-385, November.
    Full references (including those not matched with items on IDEAS)

    More about this item


    Air quality; Particulate matter; Dynamic multiple equations;

    NEP fields

    This paper has been announced in the following NEP Reports:


    Access and download statistics


    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:qut:auncer:2017_01. See general information about how to correct material in RePEc.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (School of Economics and Finance) The email address of this maintainer does not seem to be valid anymore. Please ask School of Economics and Finance to update the entry or send us the correct email address. General contact details of provider: .

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service hosted by the Research Division of the Federal Reserve Bank of St. Louis . RePEc uses bibliographic data supplied by the respective publishers.