Discussion Paper
Comparing predictive accuracy I: an asymptotic test
Abstract: We propose and evaluate an explicit test of the null hypothesis of no difference in the accuracy of two competing forecasts. In contrast to previously developed tests, a wide variety of accuracy measures can be used (in particular, the loss function need not be quadratic, and need not even be symmetric), and forecast errors can be non-Gaussian, nonzero mean, serially correlated and contemporaneously correlated.
Keywords: Econometrics;
Access Documents
File(s): File format is application/pdf http://www.minneapolisfed.org/research/common/pub_detail.cfm?pb_autonum_id=50
Bibliographic Information
Provider: Federal Reserve Bank of Minneapolis
Part of Series: Discussion Paper / Institute for Empirical Macroeconomics
Publication Date: 1991
Number: 52