We propose information theoretic tests for serial independence and linearity in time series. The test statisticsare based on the conditional mutual information, a general measure of dependence between lagged variables. In caseof rejecting the null hypothesis, this readily provides insights into the lags through which the dependence arises.The conditional mutual information is estimated using the correlation integral from chaos theory. The signi[tanceof the test statistics is determined with a permutation procedure and a parametric bootstrap in the testsfor serial independence and linearity, respectively.The size and power properties of the tests are examined numerically and illustrated with applications to somebenchmark time series.
serial independence linearity bootstrap permutation test nonparametric estimation nonlinear time series analysis correlation integral