The Granger-Engle procedure consists of two steps. In the first step, a lon
g-run cointegrating relationship is estimated, and in the second stage, thi
s estimated long-run relationship is used to estimate a distributed lag mod
el. This paper establishes the limit distribution of the second-stage estim
ator if the model estimated in the second stage is other than linear. One m
ay expect that the estimation of the cointegrating relationship does not af
fect the limit distribution of the second-stage estimator; however, it is s
hown that unless a regularity condition holds, this intuition is false. Cle
arly this regularity condition holds in the standard linear case. A simple
example where the limit distribution changes is the addition of the square
of the cointegrating relationship to the second stage distributed lag model
that is estimated by least squares. Surprisingly however, it turns out tha
t if a constant is included in the long-run least-squares regression, the (
possibly nonlinear) second-stage estimator will be asymptotically normally
distributed. (C) 2001 Elsevier Science S.A. All rights reserved. JEL classi
fication. C22; C32.