Vector autoregressive model approach for forecasting outflow cash in Central Java

Multivariate time series model is more applied in economic and business problems as well as in other fields. Applications in economic problems one of them is the forecasting of outflow cash. This problem can be viewed globally in the sense that there is no spatial effect between regions, so the mode...

Full description

Saved in:
Bibliographic Details
Published inJournal of physics. Conference series Vol. 1025; no. 1; pp. 12105 - 12114
Main Authors hoyyi, Abdul, Tarno, I Maruddani, Di Asih, Rahmawati, Rita
Format Journal Article
LanguageEnglish
Published Bristol IOP Publishing 01.05.2018
Subjects
AIC
Autoregressive models
Cash
Criteria
Data analysis
Economic forecasting
Economic models
OLS
Outflow
Parameter estimation
Physics
VAR
White noise
Central Java Indonesia
Indonesia
Online AccessGet full text

Cover

More Information
Summary:Multivariate time series model is more applied in economic and business problems as well as in other fields. Applications in economic problems one of them is the forecasting of outflow cash. This problem can be viewed globally in the sense that there is no spatial effect between regions, so the model used is the Vector Autoregressive (VAR) model. The data used in this research is data on the money supply in Bank Indonesia Semarang, Solo, Purwokerto and Tegal. The model used in this research is VAR (1), VAR (2) and VAR (3) models. Ordinary Least Square (OLS) is used to estimate parameters. The best model selection criteria use the smallest Akaike Information Criterion (AIC). The result of data analysis shows that the AIC value of VAR (1) model is equal to 42.72292, VAR (2) equals 42.69119 and VAR (3) equals 42.87662. The difference in AIC values is not significant. Based on the smallest AIC value criteria, the best model is the VAR (2) model. This model has satisfied the white noise assumption.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1025/1/012105