Joint Diagnostic Tests for Conditional Mean and Variance Specifications

This article proposes a general class of joint diagnostic tests for parametric conditional mean and variance models of possibly nonlinear and/or non-Markovian time series sequences. The new tests are based on a generalized spectral approach and, contrary to existing procedures, they do not need to choose a lag order depending on the sample size or to smooth the data. Moreover, they are robust to higher order dependence of unknown form. It turns out that the asymptotic null distributions of the new tests depend on the data generating process, so a bootstrap procedure is proposed and theoretically justified. A simulation study compares the finite sample performance of the proposed and competing tests and shows that our tests can play a valuable role in time series modelling. An application to the S&P500 highlights the merits of our approach.