Statistical Tests for Multiple Forecast Comparison
2012 (English)In: Journal of Econometrics, ISSN 0304-4076, E-ISSN 1872-6895, Vol. 169, no 1, 123-130 p.Article in journal (Refereed) Published
We consider a multivariate version of the Diebold-Mariano test for equal predictive ability of three or more forecasting models. The Wald-type test, S, which has a null distribution that is asymptotically chi-squared, is shown to be generally invariant with respect to the ordering of the models being compared. Finite-sample corrections for the test are also developed. Monte Carlo simulations indicate that S has reasonable size properties in large samples but tends to be oversized in moderate samples. The finite-sample correction succeeds in correcting for size, but only partially. For the size-adjusted tests, power increases with sample size, as expected. It is speculated that further finite-sample improvements can be achieved using Hotelling's T-2 or bootstrap critical values.
Place, publisher, year, edition, pages
2012. Vol. 169, no 1, 123-130 p.
forecast comparison, multivariate tests of equal predictive ability, dieboldâMariano test, finite-sample correction
IdentifiersURN: urn:nbn:se:uu:diva-97032DOI: 10.1016/j.jeconom.2012.01.014ISI: 000306046900012OAI: oai:DiVA.org:uu-97032DiVA: diva2:171805