This paper proposes an ADF coeﬀicient test for detecting the presence of a unit root in ARMA models of unknown order. Our approach is fully parametric. When the time series has an unknown deterministic trend, we propose a modiﬁed version of the ADF coeﬀicient test based on quasi-diﬀerencing in the construction of the detrending regression as in Elliot, Rothenberg and Stock (1996). The limit distributions of these test statistics are derived. Empirical applications of these tests for common macroeconomic time series in the US economy are reported and compared with the usual ADF t-test.