Evidence on nonlinear error correction in money demand: the case of Taiwan

Abstract

This paper proposes a nonlinear error-correction model based upon smooth transition regression methodology. The model is speci® ed such that the short-run adjustment toward long-run equilibrium is nonlinear and that the error correction is a smooth function of long-run deviation. Empirical results obtained from estimating M2 money demand in Taiwan support the hypothesis of a nonlinear error-correction process and provide better interpretation of change in the demand for money.

Currency substitution and nonlinear error correction in Taiwan's demand for broad money

“…Therefore, we find that the estimated cointegrating coefficients are all significantly different from 0. According to the long-run relationship, we find that income elasticity is 1.54 and the interest semi-elasticity is -0.08, which are consistent with those in Arize (1994) andHuang andLin (2001). Furthermore, the negative impact of real exchange rates on real money balances indicates the dominant effect of currency substitution.…”

“…Many articles have adopted a non-linear approach to examining the dynamics of money demand (Sarno et al, 2003;Sarno, 1999; , Eliasson and svirta a Ter & & 2001;and Huang et al, 2001), and all of these papers provide a non-linear analysis to the money demand for a single country. Their findings point out that a non-linear model, such as a smooth transition autoregressive model (STAR), is appropriate to discuss the dynamics of money demand.…”

An Extremely-Low-Interest-Rate Policy and the Shape of the Japanese Money Demand Function

“…6. Applications of the smooth transition model for modeling the money demand equation include Wolters et al (1998), Lütkepohl et al (1999), Sarno (1999), Huang et al (2001), and Teräsvirta and Eliasson (2001). Unlike the present paper, these studies all assume a linear long-run relation between money and other variables that is based on economic theories for money demand, thus using a smooth transition error correction model to capture nonlinear dynamics of a short-run correction process to a long-run equilibrium.…”

Testing linearity in a cointegrating STR model for the money demand function: International evidence from G-7 countries

“…These are the target-bounds model and the buffer stock model. 2 Moreover, the variations in money will tend to be more volatile in an economic downturn than in an upswing [24]. The money demand is more responsive to the interest rate when the rate is higher.…”