The Hodrick-Prescott filter is often applied to economic series as part of the study of business cycles. Its properties have most frequently been explored through the development of essentially asymptotic results which are practically relevant only some distance from series endpoints. Our...

In this paper we introduce a new test of the null hypothesis of no cointegration between a pair of time series. For a very simple generating model, our test compares favourably with the Engle-Granger/Dickey-Fuller test and the Johansen trace test. Indeed, shortcomings of the former motivated the...

Although the t-ratio variant of the Dickey-Fuller test is the most commonly applied unit-root test in practical applications, it has been known for some time that readily implementable, more powerful modifications are available. We explore the large-sample properties of five of these modified...

Unit root tests, seeking mean or trend reversion, are frequently applied to panel data. We show that more powerful variants of commonly applied tests are readily available. Moreover, power gains persist when the modifications are applied to bootstrap procedures that may be employed when...

Assume that a time series is generated by an autoregression which has atmost one unit root. A correctly specified model, including linear time trend, is estimated by ordinary least squares, but no allowance is made for any unit root in the generating process. We investigate the impact of...

Although the t-ratio variant of the Dickey-Fuller test is the most commonly applied unit-root test in practical applications, it has been known for some time that readily implementable, more powerful modifications are available. We explore the large-sample properties of five of these modified...

This study considers the possibility of estimating a Dickey-Fuller regression, constraining the autoregressive parameter to be at most one, and imposing prior knowledge of the sign of the drift parameter. In spite of apparently encouraging asymptotic results, it emerges that no feasible test of...

We apply the idea of using reversed time series to improve the power of Johansen tests. We suggest computationally simple variants of the trace and maximum eigenvalue statistics and establish their limit distributions. Both are shown, via simulation, to yield nontrivial power gains.

Although the t-ratio variant of the Dickey-Fuller test is the most commonly applied unit root test in practical applications, it has been known for some time that readily implementable, more powerful modifications are available. We explore the large sample properties of five of these modified...