Testing Interval Forecasts: A GMM-Based Approach
Version of Record online: 28 NOV 2011
Copyright © 2011 John Wiley & Sons, Ltd.
Journal of Forecasting
Volume 32, Issue 2, pages 97–110, March 2013
How to Cite
Dumitrescu, E.-I., Hurlin, C. and Madkour, J. (2013), Testing Interval Forecasts: A GMM-Based Approach. J. Forecast., 32: 97–110. doi: 10.1002/for.1260
- Issue online: 28 JAN 2013
- Version of Record online: 28 NOV 2011
- Manuscript Received: 23 AUG 2011
- Manuscript Accepted: 23 AUG 2011
- interval forecasts;
- high-density region;
This paper proposes a new evaluation framework for interval forecasts. Our model-free test can be used to evaluate interval forecasts and high-density regions, potentially discontinuous and/or asymmetric. Using a simple J-statistic, based on the moments defined by the orthonormal polynomials associated with the binomial distribution, this new approach presents many advantages. First, its implementation is extremely easy. Second, it allows for a separate test for unconditional coverage, independence and conditional coverage hypotheses. Third, Monte Carlo simulations show that for realistic sample sizes our GMM test has good small-sample properties. These results are corroborated by an empirical application on SP500 and Nikkei stock market indexes. It confirms that using this GMM test leads to major consequences for the ex post evaluation of interval forecasts produced by linear versus nonlinear models. Copyright © 2011 John Wiley & Sons, Ltd.