Parameter Estimation of GARCH Model with Bootstrap Approximation

Penaksiran Paramater Model GARCH Menggunakan Pendekatan Bootstrap

Abstract

This study aims to estimate the parameters of the Generalized Autoregressive Conditional Heteroscedasticity (GARCH) model using a bootstrap approach. In the heteroscedasticity data model, it is determined how much the residual value of the sample used is. The bootstrap approach is a non-parametric and resampling technique used to estimate the parameter. From the sample data implemented, the residual estimation using the Maximum Likelihood Estimation method is - 0.065851304. Furthermore, the residual estimation value using the bootstrap approach is -1.769129241. Thus, the use of the bootstrap approach in the GARCH model results in a smaller residual value than MLE.