This study is using the multivariate autoregressive model for detecting the causality direction of six economic variables, which are price level, money, wage, real GNP, unemployment, and import prices in Korea.
So far, we have tried to show the true relationship among the price level and relevant factors. But which of them are exogenous (or endogenous) variables? This is one of the main problems in modeling of econometrics.
In a recent paper Sims (1980) has criticized the haphazard way conventional econometric models were constructed. His main point is that the true structural relationship governing the probability distribution of economic variables is very complex, and yet in practice econometricians achieve identification of their models by imposing false or spurious a priori restrictions. If a model is specified according to a set of incorrect laws, statistical inference based on it will be meaningless. (Hsiao)
Thus this study treats six variables as jointly dependent and fit a vector autoregressive model for these variables to avoid imposing false or spurious restrictions and, in the next atage, we interprete the empirical results, concerning economic contents. This is an appealing approach for a set of stationary variables. Economic theory is used only to the extent of selecting a proper set of variables for analysis in model specification.
In addition, this study suggests how to revise the test procedure and the definition of causality (feedback) in the empirical test. After this empirical test, we obtain the conclusion that money is only exogenous variable and a driving force to other variables.
Of course there may be many results for the relationships among six variables (P,M,W,G,U,V), and so some will be interpreted in this paper.