ARCH, GARCH and EGARCH Models: Applications to Financial Series

Abstract

This article includes a description of the ARCH, GARCH, and EGARCH models and the estimation of their parameters using maximum likelihood. An alternative model is proposed for the analysis of financial series and used to study price and returns series for Gillette stock. The choice of models using AIC and BIC criteria lead us to conclude that, of the models considered, GARCH (1,2) best explains the performance of stock prices and EGARCH (2,1) best explains the returns series.

Note: Downloadable document is in Spanish.

Keywords: ARCH, GARCH, and EGARCH models, prediction

JEL Classification: C10, C19, C32, G10