MODEL RUNTUN WAKTU UNTUK MEMODELKAN DATA DERET BERKALA JANGKA PANJANG

• Main Authors: , DEWINTA PUTRI, , Yunita Wulan Sari, S.Si., M.Sc.
• 格式: Theses and Dissertations NonPeerReviewed
• 出版: [Yogyakarta] : Universitas Gadjah Mada 2014
• 主題: ETD
• 在線閱讀: https://repository.ugm.ac.id/132351/; http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=72881

There are two types of data are known in the analysis of time series that are short memory and long memory. Short memory is data that has a characteristic process of short-term memory while long memory is data that has a characteristic process of long-term memory. The long memory data is only capable of long accurately analyzed using ARFIMA (Autoregressive Fractionally Integrated Moving Average). The purpose of this thesis to explain how to do data modeling with appropriate ARFIMA method with steps of data analysis by the method of Box Jenkins were able to apply these forecasting methods to real data. Data time series that are characterized by long memory has autocorrelation function plot (Autocorrelation Function (ACF)) which does not go down exponentially but slowly declining or hyperbolic. ARFIMA model is the development of models Autoregressive Integrated Moving Average Model ( ARIMA ), with the value of the distinction ( differencing ) is real value. In writing this essay, identification of order parameter is done by looking at the ACF and PACF correlogram. ARFIMA modeling steps are as follows: 1. normality test for long memory data