VaR is a market risk measurement approach that uses the statistical analysis of historical market trends and volatilities to estimate the likelihood that a given portfolio’s losses will exceed a certain amount. It measures the largest loss likely to be suffered on a portfolio position over a holding period (usually 1 to 10 days) with a given probability (confidence level). As an example, assuming a 99% confidence level, the losses will exceed VaR with a probability of 1% or in other words what would be the worst day in 100 days.
VaR can be calculated using a number of approaches such as the Variance Covariance Approach, the Historical Simulation Approach, the Monte Carlo Simulation Approach, etc.