Author(s)

R. Dios & J. A. Roldan

Abstract

This paper analyzes the unit root test proposed by Dickey and Fuller taking into account the no-similarity. Exactly, we consider a Gaussian first-order autoregressive process with unknown intercept where the initial value of the variable is a known constant. We propose an unusual two-sided test of the random walk hypothesis since it involves two distributions (Nankervis and Savin, 1985) where the acceptance region is constructed by taking away equal areas for the upper tail of the Student's t distribution and the lower tail of the distribution tabulated by Dickey and Fuller under the null hypothesis of unit root. In some cases, the critical values tabulated by Dickey and Fuller does not allow us to reject the hypothesis of a unit root, while we can reject if we use Studen

Keywords