The effects of risk modelling: assessing value-at-risk accuracy

This study examines Value-at-Risk (VaR) models that are integrated with several volatility representations to estimate the market risk for seven nonfinancial sectors traded on the first board of the Malaysian stock exchange. In a sample that spanned 19 years from1993 until 2012 for construction, consumer product, industrial product, plantation, property, trade and services and mining sectors, the expected maximum losses are quantified at 95% confidence level. For accuracy determination, assessments using Kupiec test and Christoffersen test have provided evidence that almost every model are found to be accurate for all sets of occurrence. However, using the Lopez test which takes into consideration the magnitude of the impact of exceptions, the most accurate model is the VaR which is integrated with GARCHt. This study found that fat tails and asymmetries are important issues that need to be considered when estimating VaR in managing financial risks.