Money Demand in Korea: A Cointegration Analysis, 1973-2014

Abstract

This paper estimates the demand for real money in Korea over the 1973Q3 to 2014Q4 period via unit root and cointegration methods. Utilizing the Johansen cointegration methodology and the Pantula principle, it establishes that a long-term relationship exists among the included variables. The paper also estimates an error correction model (ECM) as well as a vector error correction model (VECM), extending previous analyses by performing forecasts and testing for Granger causality among the variables. It finds that the broader definition of money, M2, serves as a relatively better measure of the money aggregate than M1 when evaluating the stability of the real demand for money. The long-term interest (LR) rate also seems to provide better results than the short-term rate (SR), which is consistent with economic theory given that it refers to a long-run equilibrium relationship. Both the ECM and VECM estimates showed the expected (and significant) signs on the coefficients; LM2 (LM1) and LGDP were positively related and LM2 (LM1) and LR (SR) were negatively related. Granger block causality tests and impulse response functions together seem to suggest that the traditional money demand function which places M as its ‘dependent’ variable, while including income and interest rates as its regressors, was a robust and stable model in the case of Korea.