1.  Measures the potential loss in value of a risky asset or portfolio over a defined period for a given confidence interval  For example: ◦ If the VaR on an asset is $100,000 at a one-week, 95% confidence level, then there is only a 5% chance that the value of the asset will drop more than $100,000 over any given week

2.  Focus is on downside risk and potential losses  Most often used by commercial and investment banks to capture the potential loss in value of their traded portfolios from adverse market movements  The VaR can be compared to available capital & cash reserves to ensure that the losses can be covered without putting firms at risk

3.  Variance-Covariance Method ◦ Using an assumed distribution for the asset return (e.g. normally distributed), estimated mean, variances & covariance, compute the associated probability for the VaR  Historical Simulation ◦ Use sorted time series data to identify the percentile value associated with the desired VaR  Monte Carlo Simulation ◦ Specify probability distributions & correlations for relevant market risk factors and build a simulation model that describes the relationship between the market risk factors and the asset return. After performing iterations, identify the return that produces the desired percentile for the VaR.

4.  Returns may not be distributed as assumed. Thus there could be more outliers than expected and the actual VaR could be much higher than the computed VaR  Variance-Covariance matrix is based on historical data, which is a collection of estimates that might have large standard errors  Variance-Covariance matrices can change over time when the fundamentals that drive these numbers change over time (e.g. oil prices)