Delgado, Miguel A.Escanciano, Juan Carlos2009-05-292009-05-292007Journal of Econometrics. 2007, vol. 141, p. 652-6820304-4076https://hdl.handle.net/10016/2494This article proposes omnibus tests for conditional symmetry around a parametric function in a dynamic context. Conditional moments may not exist or may depend on the explanatory variables. Test statistics are suitable functionals of the empirical process of residuals and explanatory variables, whose limiting distribution under the null is nonpivotal. The tests are implemented with the assistance of a bootstrap method, which is justified assuming very mild regularity conditions on the specification of the center of symmetry and the underlying serial dependence structure. Finite sample properties are examined by means of a Monte Carlo experiment.text/plainapplication/pdfeng© ElsevierOmnibus testsSymmetry testsConditional distributionsTime seriesEmpirical processesBootstrapresearch articleC12C14C15Economía10.1016/j.jeconom.2006.10.011open access