Application of GSTARI (1,1,1) Model for Forecasting the Consumer Price Index (CPI) in Three Cities in Central Java

Abstract

Economic development is affected by several factors, one of which is the inflation rate. One indicator used to measure the inflation rate is Consumer Price Index (CPI). The CPI data is recorded simultaneously at several locations over time, produces space-time data. In Central Java Province, CPI is calculated in six regency/cities, so the CPI is affected by the time and other locations named space-time effect. The forecasting methods involve space and time effect simultaneously is GSTAR. This study used the GSTAR model to forecasting the CPI in 3 cities in Central Java, assuming that autoregressive and space-time parameters differ for each location. This study aims to obtain the best GSTAR model to forecast the CPI in three cities in Central Java by using the IDW and NCC weighting. The results indicated that the best GSTAR model for forecast the CPI in three cities (Surakarta, Semarang, and Tegal) was the GSTARI (1,1,1) model. The GSTARI (1,1,1) model fulfils the assumption of homoscedasticity, white noise, and multivariate normal. The MAPE values obtained using the IDW and NCC weighting are 0.2922% and 0.2914%, respectively. From these results, it can be concluded that the best GSTARI (1,1,1) model to forecast the CPI data in three cities in Central Java is NCC weights, as they have a minimum MAPE value . The results of this research can be used as consideration for the government in making economic policies at the present and in the future.

Keywords

• space time
• autoregressive
• gstar model
• invers distance
• cross correlation