Modeling Data Containing Outliers using ARIMA Additive Outlier (ARIMA-AO)
Ansari Saleh Ahmar, Suryo Guritno, Abdurakhman, Abdul Rahman, Awi, Alimuddin, Ilham Minggi, M Arif Tiro, M Kasim Aidid, Suwardi Annas, Dian Utami Sutiksno, Dewi Satria Ahmar, Kurniawan H Ahmar, A Abqary Ahmar, Ahmad Zaki, Dahlan Abdullah, Robbi Rahim, Heri Nurdiyanto, Rahmat Hidayat, Darmawan Napitupulu · Journal of Physics Conference Series · 2018
The aim this study is discussed on the detection and correction of data containing the additive outlier (AO) on the model ARIMA (p, d, q). The process of detection and correction of data using an iterative procedure popularized by Box, Jenkins, and Reinsel (1994). By using this method we obtained an ARIMA models were fit to the data containing AO, this model is added to the original model of ARIMA coefficients obtained from the iteration process using regression methods. In the simulation data is obtained that the data contained AO initial models are ARIMA (2,0,0) with MSE = 36,780, after the detection and correction of data obtained by the iteration of the model ARIMA (2,0,0) with the coefficients obtained from the regression Z t = 0,106+0,204 Z t −1 +0,401 Z t −2 −329 X 1 ( t )+115 X 2 ( t )+35,9 X 3 ( t ) and MSE = 19,365. This shows that there is an improvement of forecasting error rate data.