A comparative study of error distributions in the GARCH model through a Monte Carlo simulation approach

Samuel Ampadu, Eric T. Mensah, Eric N. Aidoo, Alexander Boateng, Daniel Maposa

Research output: Contribution to journalArticlepeer-review

24 Downloads (Pure)

Abstract

Financial time series data are known to exhibit volatility clustering, which implies that the volatility of financial returns tends to persist over time. This phenomenon has significant implications for risk management and financial decision-making. To capture this volatility clustering effect, the Generalized Autoregressive Conditional Heteroscedasticity (GARCH) model is widely used. Through a Monte Carlo simulation experiment, the performance GARCH-type model with five different error distribution specifications were compared. The study found that the Skewed Generalized Error Distribution (SGED) was the most efficient and consistent distribution for modelling financial time series. The SGED outperformed the Normal, Student's t, GED, and skewed Student's t distributions in terms of goodness-of-fit, MSE, MAE and different sample sizes. The study suggests that the SGED may be more suitable for modelling financial time series with a GARCH-type specification in general contexts.

Original languageEnglish
Article numbere01988
JournalScientific African
Volume23
Early online date22 Nov 2023
DOIs
Publication statusPublished - Mar 2024

Keywords

  • Error distributions
  • Financial time series
  • GARCH model
  • Skewed generalized error distribution

ASJC Scopus subject areas

  • General

Fingerprint

Dive into the research topics of 'A comparative study of error distributions in the GARCH model through a Monte Carlo simulation approach'. Together they form a unique fingerprint.

Cite this