School of Economics and Finance

No. 609: A Test for Serial Dependence Using Neural Networks

George Kapetanios , Queen Mary, University of London

October 1, 2007

Download full paper


Testing serial dependence is central to much of time series econometrics. A number of tests that have been developed and used to explore the dependence properties of various processes. This paper builds on recent work on nonparametric tests of independence. We consider a fact that characterises serially dependent processes using a generalisation of the autocorrelation function. Using this fact we build dependence tests that make use of neural network based approximations. We derive the theoretical properties of our tests and show that they have superior power properties. Our Monte Carlo evaluation supports the theoretical findings. An application to a large dataset of stock returns illustrates the usefulness of the proposed tests.

J.E.L classification codes: C32, C33, G12

Keywords:Independence, Neural networks, Strict stationarity, Bootstrap, S&P500