Comparison of Spatial Weights in Modeling Inflation and Money Supply Using the Spatial Vector Autoregressive Model with Calendar Variations

Abstract

Abstract In modeling inflation and the money supply simultaneously using SpVAR with calendar variations, it is necessary to have the appropriate spatial weight. There are several spatial weights that can be used, including uniform weight, inverse distance weight and weight based on normalization of cross correlation. This study aims to compare the three spatial weights for modeling inflation and the money supply simultaneously using the SpVAR model with calendar variations. The results of this study indicate that the weight based on normalization of cross correlation is the best spatial weight for modeling inflation and the money supply simultaneously using the SpVAR model with calendar variations because it produces the model with the smallest Mean Square Error (MSE)..