The asymptotic distribution of the least-squares estimators in the ran
dom walk model was first found by White [17] and is described in terms
of functionals of Brownian motion with no closed form expression know
n. Evans and Savin [5,6] and others have examined numerically both the
asymptotic and finite sample distribution. The purpose of this paper
is to derive an asymptotic expansion for the distribution. Our approac
h is in contrast to Phillips [12,13] who has already derived some term
s in a general expansion by analyzing the functionals. We proceed by a
ssuming that the errors are normally distributed and expand the charac
teristic function directly. Then, via numerical integration, we invert
the characteristic function to find the distribution. The approximati
on is shown to be extremely accurate for all sample sizes greater-than
-or-equal-to 25, and can be used to construct simple tests for the-pre
sence of a unit root in a univariate time series model. This could hav
e useful applications in applied economics.