There is a vast amount of empirical evidence concerning the cointegrating relationship between money demand, some kind of
interest rate and income. In contrast to this, short-run dynamics are still opaque. In the existing literature, the return
to steady state is modelled quite differently. The range goes from simple error correction models to non-linear approaches.
Here a method is proposed for considering not only disequilibria between money demand and its steady state of only the last
period but also those of the recent past in a parsimonious and economically meaningful way. Different to multicointegration,
weights for cumulating steady-state deviations are geometrically decreasing the more they are located in the past. This model
possesses an ARMA (1,1) representation and leads to an ARMAX model if combined with a conventional error correction model.
This approach is shown to track money demand short-run dynamics better and more parsimoniously than partial-adjustment models.