THE ANALYSIS OF INDONESIA INFLATION DATA USING BOX-JENKINS MODELS

Inflation is a sustained increase in the general price level of goods and services in an over a period of time. Inflation's effects on an economy are various and can be simultaneously positive and negative. Negative effects of inflation include an increase in the opportunity cost of holding money and uncertainty over future inflation which may discourage investment and savings. The aims of this research are to analyze the Indonesia inflation data using Box-Jenkins models and to find the best model based on the smallest Mean Squared Error (MSE). Then by using this model, the inflation value of some period ahead will be predicted. Based on the historical data of Indonesia year-on-year inflation data from December 2006 until December 2013, known that the best Box-Jenkins model is subset ARIMA ([1,12],1,0). The MSE of the model reach into 0.274 and the MAPE is equal 4.36%. The prediction inflation in 2014 is 4.28%. Keywords: Inflation, Indonesia, subset ARIMA, MSE, MAPE