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

Ahmar, Ansari Saleh and Gurtino, Suryo and Abdurakhman, Abdurakhman and Rahman, Abdul and Dassa, Awi and Alimuddin, Alimuddin and Minggi, Ilham and Tiro, M Arif and Aidid, M Kasim and Annas, Suwardi and Sutiksno, Dian Utami and Ahmar, Kurniawan H and Ahmar, A Abqary and Zaki, Ahmad and Abdullah, Dahlan and Rahim, Robbi and Nurdiyanto, Heri and Hidayat, Rahmat and Napitupulu, Darmawan and Simarmata, Janner and Kurniasih, Nuning and Abdillah, Andretti Leon and Pranolo, Andri and Haviluddin, Haviluddin and Albra, Wahyudin and Arifin, A Nurani M (2018) Modeling Data Containing Outliers using ARIMA Additive Outlier (ARIMA-AO). In: Joint Workshop of KO2PI & 2nd International Conference on Mathematics, Science, Technology, Education, and their Applications (2nd ICMSTEA), 3-4 Oktober 2016, Grand Clarion Hotel, Makassar.

This is the latest version of this item.

[img] Text (Artikel Prosiding)
Ahmar_2018_J._Phys.__Conf._Ser._954_012010.pdf

Download (827kB)
[img] Text (Turnitin)
1. Ahmar_2018_J._Phys.__Conf._Ser._954_012010 Turnitin.pdf

Download (906kB)
Official URL: https://iopscience.iop.org/article/10.1088/1742-65...

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 Zt = 0,106+0,204Zt−1+0,401Zt−2−329X1(t)+115X2(t)+35,9X3(t) and MSE = 19,365. This shows that there is an improvement of forecasting error rate data.

Item Type: Conference or Workshop Item (Paper)
Subjects: FMIPA > PENDIDIKAN MATEMATIKA - (S1)
FMIPA > Matematika
Divisions: FAKULTAS MIPA
Depositing User: Zainatun
Date Deposited: 30 Jun 2023 13:39
Last Modified: 30 Jun 2023 13:39
URI: http://eprints.unm.ac.id/id/eprint/32708

Available Versions of this Item

Actions (login required)

View Item View Item