Study of X-13 ARIMA SEATS Modeling for Rice Price Index Data in Indonesia

Outlier on a data can cause several problems, including a model that is formed to produce a large residual, and the variance of data will increase. A robust method for outlier problems is needed in order to produce an unbiased model. X-13 ARIMA SEATS is one of robust method in time series. X-13 ARIM...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2021-03, Vol.1863 (1), p.12055
Main Authors: Putri, Agnes Maludfi, Sadik, Kusman, Afendi, Farit Mochamad
Format: Article
Language:English
Subjects:
Autoregressive models
Data analysis
Model testing
Outliers (statistics)
Physics
Robustness
Seats
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Outlier on a data can cause several problems, including a model that is formed to produce a large residual, and the variance of data will increase. A robust method for outlier problems is needed in order to produce an unbiased model. X-13 ARIMA SEATS is one of robust method in time series. X-13 ARIMA SEATS is a seasonal adjustment method capable of detecting, resolving the presence of outliers, and overcoming seasonal and calendar effect. The X-13 ARIMA SEATS consists of two stages that is using regARIMA model, and using X-12 seasonal adjustment. In this paper, X-13 ARIMA SEATS method is compared with ARIMA method to prove its ability to overcome outliers based on the smallest error value. In this paper, the X-13 ARIMA SEATS method is applied to model and forecast the rice price index in Indonesia in January 2010-December 2018. The results showed that the X-13 ARIMA SEATS method produces a model with smaller MAPE and RMSE values than the ARIMA model.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1863/1/012055