MULTIVARIATE AUTOREGRESSIVE MODEL FOR FORECASTING THE DEMAND OF CONTAINER THROUGHPUT IN INDONESIA

Syafi’i, (2006) MULTIVARIATE AUTOREGRESSIVE MODEL FOR FORECASTING THE DEMAND OF CONTAINER THROUGHPUT IN INDONESIA. MEDIA TEKNIK SIPIL, 6 (2). pp. 129-135. ISSN 1412-0976

[img] PDF - Published Version
Download (214Kb)

    Abstract

    Abstract This research was proposed to forecast the demand of container throughput in Indonesia. The analysis was carried out in multivariate autoregressive model. Augmented Dickey-Fuller (ADF) test was used to check the stationarity of data and order of integration. Johansen approach was used to find the existence and the number of cointegration relationship. The number of cointegration relations was established by a sequential likelihood ratio test on the rank of an estimated parameter matrix from vector error correction model (VECM), impulse response function (IRF) was performed to know response to a shock of a variable of other variables. The empirical analysis demonstrated that the estimation model provides indication of goodness-of-fit and the forecasting potential of the model. Most of the model estimation results follow the long-term development of the actual data series closely. The impulse response of a shock of a variable to itself and other variables die out after certain period. These results verified the stability of all the estimated models. The forecast of container throughput in Indonesia generated by VECM indicated the reasonable result. Keywords: container throughput, forecasting, multivariate autoregressive.

    Item Type: Article
    Subjects: T Technology > TA Engineering (General). Civil engineering (General)
    Divisions: Fakultas Teknik > Teknik Sipil
    Depositing User: Desi Arista
    Date Deposited: 11 Jul 2013 12:54
    Last Modified: 11 Jul 2013 12:54
    URI: https://eprints.uns.ac.id/id/eprint/1252

    Actions (login required)

    View Item