An empirical comparison of alternative models in estimating Value-at-Risk: evidence and application from the LSE

Abstract

This paper compares a select number of Value-at-Risk (VaR) models using daily data from the London stock exchange for estimating the model-based VaR. The period covers volatile market conditions triggered by a host of events that induced market uncertainty. Our results provide an indication of the degree of accuracy of the various methods and discuss issues of model selection. The empirical findings suggest that the Equally Weighted Moving Average (EWMA) model can furnish more accurate estimated VaR than the GARCH methods, including the popular Historical Simulation (HS) approach, by altering the estimation horizon.