EN
In this article an alternative method for analysis the integration of time series is proposed. The procedure is appropriate in the presence of outliers and was called 'linearized Dickey-Fuller test'. The method is based on the assumption that the data is generated by some ARIMA (Autoregressive integrated moving average) proces. In the first step, the outliers are identified on the basis of likelihood ratio tests, using REGARIMA model. Then, the estimated effect of outliers is removed from the data. In the last step, the Dickey-Fuller test is applied to the adjusted series. It is shown, via simulations, that the procedure leads to the unit root test with accurate finite sample size and considerably improved power.