Integration of Almon and GARCH Methods to Overcome Heteroscedasticity Problems in Economic Time Series Analysis

Oktariana, Salsa Agung
Putra, Muhammad Rafael Andika

Indonesian Journal of Mathematics and Applications
Vol. 3 No. 1 (2025): Indonesian Journal of Mathematics and Applications (IJMA)

Homoscedasticity is an important assumption for statistical models, one of which is linear regression models from economic aspects which generally have time series type data. The Almon method is one approach used to handle lag effects in time series data. However, the residuals produced by the Almon method do not meet the assumption of homoscedasticity. To overcome this, it is necessary to handle the residuals from the Almon method using the GARCH (Generalized Autoregressive Conditional Heteroskedasticity) model. This research uses 4 different types of GARCH models. The GARCH (1,1) model is the most appropriate model as evidenced by the smallest BIC value, namely 18.19199. The result was that the GARCH (1,1) model could handle the heteroskedasticity problem in the Almon method residuals.