@article{Stock-Adjustment:670, recid = {670}, author = {Amano, Robert and Wirjanto, Tony S.}, title = {The Implications of Nonstationarity for the Stock-Adjustment Model}, publisher = {Bank of Canada}, address = {1993}, pages = {1 online resource (v, 28 pages)}, abstract = {This paper studies the asymptotic behaviour of least squares estimates in a stock adjustment model when the variables are nonstationary. The paper first considers the case in which the variables are not cointegrated, and then examines the case under cointegration. In the case of no cointegration, we find that the least squares estimate of the adjustment coefficient is close to zero, independent of its true value. In the case of cointegration, it is shown that a transformation can be applied to the model so that the resulting instrumental variable estimates will have standard distributions. Economic examples are used to illustrate each case and Monte Carlo simulations are performed in order to gauge the relevance of the asymptotic results for finite samples. The simulation evidence suggests that the asymptotic results are useful approximations in finite samples.}, url = {http://www.oar-rao.bank-banque-canada.ca/record/670}, doi = {https://doi.org/10.34989/swp-1993-1}, }