Value At Risk (VaR)
VaR – It is a measure of the amount that can be lost from the position, portfolio, desk, bank, etc. VaR is generally understood that quantifies the extent of potential financial losses an investment could incur at a given confidence level over a specified time horizon. There are other risk measures used in practice, but this is the simplest, most popular, and most common.
For example, if the VaR for one day at a 95% confidence level is INR 100,000, it means that 5 days out of 100 portfolio can expect to lose more than INR 100,000.
Methods to Calculate VaR
1. Historical Method – It is a non-parametric method that involves sorting returns in ascending order and identifying the loss threshold corresponding to the desired confidence level.
2. Variance-Covariance Method – It is a parametric approach that assumes returns are normally distributed. It requires estimating the mean and standard deviation of returns and using these parameters to calculate the VaR at the desired confidence level.
3. Monte Carlo Simulation – This method generates a large number of random scenarios based on a specified probability distribution. Each scenario represents a possible outcome for the investment or portfolio. The VaR is calculated by sorting the simulated returns and determining the loss threshold corresponding to the desired confidence level.
Types of VaR
1. Incremental Value at Risk (IVaR) – IVaR measures the impact of small changes resulting from different positions of the portfolio on the VaR. It is obtained by repeatedly calculating VaR considering different positions of the portfolio. The difference between the new VaR and the original VaR is the IVaR.
2. Marginal Value at Risk (MVaR) – MVaR measures the impact of removing a position from a portfolio on the overall VaR. Unlike IVaR, it measures the impact of removing an entire portfolio holding rather than making small changes in the portfolio position on VaR.
3. Component Value at Risk (VaR) – The concept of component VaR is linked to MVaR. It can be thought of as VaR expressed in a dollar amount. Component VaR is calculated by finding the weight of the position being deleted from the overall portfolio.
4. Conditional Value at Risk (CVaR) – CVaR is the extended risk measure of VaR that quantifies the average loss over a specified time period of unlikely scenarios beyond the confidence level. It is also known as Expected Shortfall.
5. Relative VaR – Relative VaR measures the risk resulting from the underperformance of a portfolio relative to a benchmark portfolio.
