Modeling Data Containing Outliers using ARIMA Additive Outlier (ARIMA-AO)

Saleh Ahmar, Ansari and Suryo, Guritno and Abdurakhman, Abdurakhman and Rahman, Abdul and Dassa, Awi and Alimuddin Tampa, Alimuddin and Minggi, Ilham and ARIF TIRO, MUHAMMAD and Kasim Aidid, MUHAMMAD and Annas, Suwardi Modeling Data Containing Outliers using ARIMA Additive Outlier (ARIMA-AO). Journal of Physics: Conference Series.

[img] Text
Ahmar_2018_J._Phys.__Conf._Ser._954_012010.pdf

Download (827kB)

Abstract

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 Z Z X t X t X t t t t       0,106 0,204 0, 401 329 115 35,9   1 2 1 2 3       and MSE = 19,365. This shows that there is an improvement of forecasting error rate data.

Item Type: Article
Subjects: FMIPA
Divisions: FAKULTAS MIPA
Depositing User: Jusniar Jusniar
Date Deposited: 30 Jun 2023 04:11
Last Modified: 30 Jun 2023 04:11
URI: http://eprints.unm.ac.id/id/eprint/32540

Actions (login required)

View Item View Item