Vector autoregressive processes with nonlinear time trends in cointegrating relations

We extend the conventional cointegrated VAR model to allow for general nonl inear deterministic trends. These nonlinear trends can be used to model gra dual structural changes in the intercept term of the cointegrating relation s. A general asymptotic theory of estimation and statistical inference is r eviewed and a diagnostic test for the correct specification of an employed nonlinear trend is developed. The methods are applied to Finnish interest-r ate data. A smooth level shift of the logistic form between the own-yield o f broad money and the short-term money market rate is found appropriate for these data. The level shift is motivated by the deregulation of issuing ce rtificates of deposit and its inclusion in the model solves the puzzle of t he "missing cointegration vector" found in a previous study.