Long-Run Money Demand in Latin-American countries: A Nonestationary Panel Data Approach

Central banks have long been interested in obtaining precise estimations of money demand given the fact that the evolution of money demand plays a key role over several monetary variables. I use Pedroni's (2002) Fully Modified Ordinary Least Square (FMOLS) to estimate the coefficients of the long-run money demand function for 15 Latin-American countries. The FMOLS technique pool information regarding common long-run relationships while allowing the associated short-run dynamics and fixed effects to be heterogeneous across different members of the panel. For this group of countries, I find evidence of a cointegrating money demand, an income elasticity of 0.94, and an interest-rate semi-elasticity of -0.01.