We assume that some consistent estimator of an equilibrium relation between non-stationary fractionally integrated series is used in a first step to compute residuals (or differences thereof). We propose to apply the semiparametric log-periodogram regression to the (differenced) residuals in...

Conventional univariate Dickey-Fuller tests tend to produce spurious stationarity when there exist additive outlying observations in the time series. Correct critical values are usually obtained by adding dummy variables to the Dickey-Fuller regression. This is a nice theoretical result but not...

We assume that some consistent estimator of an equilibrium relation between non-stationary fractionally integrated series is used in a first step to compute residuals (or differences thereof). We propose to apply the semiparametric log-periodogram regression to the (differenced) residuals in...

We consider bivariate regressions of nonstationary fractionally integrated variables dominated by linear time trends. The asymptotic behaviour of the ordinary least square (OLS) estimators in this case allows limiting normality to arise at a faster rate of convergence than if the individual...

We show that OLS and GLS are asymptotically equivalent in the linear regression model with AR (p) disturbances and a wide range of trending regressors_ and that OLS based statistical inference is still meaningful after proper adjustment of the test statistics.

We show that OLS and GLS are asymptotically equivalent in the linear regression model with AR (p) disturbances and a wide range of trending regressors_ and that OLS based statistical inference is still meaningful after proper adjustment of the test statistics.

This paper is concerned with testing the null hypothesis of no cointegration among I(1) variables when the cointegration residuals are I(d) with 0 < d <1. This possibility is entertained with increasing frequency in many applications, (see e.g. Cheung and Lai 1993 Baillie and Bollerslev 1994 Booth and Tse 1995 or Baillie 1996 for examples. We consider the power of various cointegration tests both for the stationary case d < 5 and for the nonstationary case d > 5.

We show that OLS and GLS are asymptotically equivalent in the linear regression model with AR (p) disturbances and a wide range of trending regressors_ and that OLS based statistical inference is still meaningful after proper adjustment of the test statistics.