Warsono, Warsono and Kurniasari, Dian and Usman, Mustofa (2018) ANALYSIS OF DYNAMIC STRUCTURE, GRANGER CAUSALITY AND FORECASTING WITH VECTOR AUTOREGRESSION (VAR) MODELS ON CREDIT RISK DATA. Science International Lahore, 30 (1). pp. 7-16. ISSN 1013-5316

Preview

Text Science International Lahore - Warsono - Combine.pdf Download (1MB) | Preview

Abstract

This research discusses the dynamic structure, causality relationship, and forecasting using Vector Autoregressive (VAR) model approach. The dynamic structure is in the form of Impulse Response Function (IRF) and Forecast Error Variance Decomposition (FEVD). The causality analysis is conducted by using granger causality approach. Then the influence of a variable to predict other variables will be directedbyforecasting evaluation on the VAR model. This model is applied to see the relationship on Non-Performing Loan (NPL), Loan Interest Rate (LIR), Inflation (INF), and Rupiah Exchange Rate (EXR). The dynamic structure of the IRF results indicates that each variable requires more than 10 periods to reach equilibirium after experiencing shock. Based on the FEVD results the variance of forecasting errors at the beginning of the period is influenced only by the variable itself. The Granger causality test is significant for claiming a bi-directional causality between credit risk (NPLs) and loan interestrate (LIR), and there is indirect causality between inflation (INF) and credit risk (NPL), and direct causality between the rupiah exchange rate (EXR) and credit risk (NPL). The results of the forecasting evaluation indicate that this model is dynamically good enough to do the forecasting.

Item Type:	Article
Subjects:	Q Science > QA Mathematics
Divisions:	Fakultas Matematika dan Ilmu Pengetahuan Alam (FMIPA) > Prodi Matematika
Depositing User:	DIAN KURNIASARI
Date Deposited:	28 May 2018 03:43
Last Modified:	28 May 2018 03:43
URI:	http://repository.lppm.unila.ac.id/id/eprint/6921

Actions (login required)

View Item