PENDEKATAN KOREKSI KESALAHAN DALAM PERSAMAAN SIMULTAN STUDI KASUS: PENDAPATAN DAN PENAWARAN UANG DI INDONESIA

Abstract

This paper attempts to introduce and apply the error correction method to estimate the simultanous-equation models and compares its results with the similar method in the case of single equation model.
The empirical results show that the estimations in the case of simultanous-equation models have the similar conclusions with the case of single equation models since the fitted values of dependent variables in the reduced-form estimations are relatively close to its actual values. On the other hand, they will be quite diffrence if the fitted values of dependent variables in the reduced-form estimations quite differ from its actual values.
The results show that short-run changes in money supply (M) and investment (I) have significant and positive effects on income (Y) while government expenditure (G) is insignificant and that about 0,9151% of the discrepancy between the actual and the long-run, or equilibrium, value of Y is corrected each year by the single equation assumption and 0,8706% by the simultanous-equation assumption.
The results also show that short-run changes in income (Y) have significant and positive effects while interest rate (R) is insignificant on money supply (M) and that about 0,2327% of the discrepancy between the actual and the long-run, or equilibrium, value of M is corrected each year by the single equation assumption and 0,2346% by the simultanous-equation assumption.

Keywords: ordinary least square, two stages least square, error correction method.