Template-Type: ReDIF-Paper 1.0 Series: Tinbergen Institute Discussion Papers Creation-Date: 2008-11-03 Number: 08-105/4 Author-Name: Cees Diks Author-Email: c.g.h.diks@uva.nl Author-Workplace-Name: University of Amsterdam Author-Name: Valentyn Panchenko Author-Email: v.panchenko@unsw.edu.au Author-Workplace-Name: University of New South Wales Author-Name: Dick van Dijk Author-Email: djvandijk@few.eur.nl Author-Workplace-Name: Erasmus University Rotterdam Title: Out-of-sample Comparison of Copula Specifications in Multivariate Density Forecasts Abstract: This discussion paper resulted in a publication in the Journal of Economic Dynamics & Control, 34(9), 1596-1609.

We introduce a statistical test for comparing the predictive accuracy of competing copula specifications in multivariate density forecasts, based on the Kullback-Leibler Information Criterion (KLIC). The test is valid under general conditions: in particular it allows for parameter estimation uncertainty and for the copulas to be nested or non-nested. Monte Carlo simulations demonstrate that the proposed test has satisfactory size and power properties in finite samples. Applying the test to daily exchange rate returns of several major currencies against the US dollar we find that the Student's t copula is favored over Gaussian, Gumbel and Clayton copulas. This suggests that these exchange rate returns are characterized by symmetric tail dependence. Classification-JEL: C12, C14, C32, C52, C53 Keywords: Copula-based density forecast, semiparametric statistics, out-of-sample forecast evaluation, Kullback-Leibler Information Criterion, empirical copula File-Url: https://papers.tinbergen.nl/08105.pdf File-Format: application/pdf File-Size: 395821 bytes Handle: RePEc:tin:wpaper:20080105