But isn't that in a bivariate analysis. How about in in a multivariate sense, i.e., one EC(-1) coefficient that has a negative sign could bring the variables in the system to equilibrium, right? For example, GDP, exports and investment all are positively related. If they are cointegrated and normalized with respect to GDP, then only one EC(-1) need to be negative to bring the system back to equilibrium. If all negative or all positive, then the process is explosive, right?
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
But isn't that in a bivariate analysis. How about in in a multivariate sense, i.e., one EC(-1) coefficient that has a negative sign could bring the variables in the system to equilibrium, right? For example, GDP, exports and investment all are positively related. If they are cointegrated and normalized with respect to GDP, then only one EC(-1) need to be negative to bring the system back to equilibrium. If all negative or all positive, then the process is explosive, right?