Some Extensions of AsymptoticFandtTheory in Nonstationary Regressions

The author develops and extends the asymptoticF- andt-test theory in linear regression models where the regressors could be deterministic trends, unit-root processes, near-unit-root processes, among others. The author considers both the exogenous case where the regressors and the regression error are independent and the endogenous case where they are correlated. In the former case, the author designs a new set of basis functions that are invariant to the parameter estimation uncertainty and uses them to construct a new series long-run variance estimator. The author shows that theF-test version of the Wald statistic and thet-statistic are asymptoticallyFandtdistributed, respectively. In the latter case, the author shows that the asymptoticFandttheory is still possible, but one has to develop it in a pseudo-frequency domain. TheFandtapproximations are more accurate than the more commonly used chi-squared and normal approximations. The resultingFandttests are also easy to implement – they can be implemented in exactly the same way as theFandttests in a classical normal linear regression.