Stefan De Wachter , University of Oxford Richard D.F. Harris , University of Exeter Elias Tzavalis , Queen Mary, University of London
December 1, 2005
Download full paper
We investigate the influence of residual serial correlation and of the time dimension on statistical inference for a unit root in dynamic longitudinal data, known as panel data in econometrics. To this end, we introduce two test statistics based on method of moments estimators. The first is based on the generalised method of moments estimators, while the second is based on the instrumental variables estimator. Analytical results for the IV based test in a simplified setting show that (i) large time dimension panel unit root tests will suffer from serious size distortions in finite samples, even for samples that would normally be considered large in practice, and (ii) negative serial correlation in the error terms of the panel reduces the power of the unit root tests, possibly up to a point where the test becomes biased. However, near the unit root the test is shown to have power against a wide range of alternatives. These findings are confirmed in a more general set-up through a series of Monte Carlo experiments.
J.E.L classification codes: C22, C23
Keywords:Dynamic longitudinal (panel) data, Generalized method of moments, Instrumental variables, Unit roots, Moving average errors