Modelling the Volatility and Assessing the Performance of the Model: Case Study in Some Indonesia Stock Prices

Abstract

Estimating volatility of stock returns as accurate as possible is needed since the importance of volatility in theory and practice. Aim of the study is to show the process of assessing the performance of volatility model. This study presented GARCH(1,1) model for estimating volatility of daily returns of some stock prices of Indonesia over the period from 12 July 2007 to 29 September 2015. Parameters of the model were estimated by Maximum Likelihood Estimation. The fitted volatility series were estimated by using natural cubic spline in order to study the behavior of the volatility over the period. The performance of how good the GARCH(1,1) can capture the volatility is assessed by using Monte Carlo Simulation. The result shows that the GARCH(1,1) gives fitted volatility which is close to assumed volatility. This indicates that the GARCH(1,1) is able to capture the volatility quite well.