Value at risk is a statistic technique that measures and estimates the level of financial risk within an organization or investment portfolio or position over a specific time frame (holding period). The three major methods are used to calculate VaR are (i) Parametric Estimates (ii) Monte Carlo simulation (iii) Historical simulation.
Parametric Estimates: The method estimates VaR using parameters such as volatility and correlation. Parametric uses a relationship between variables (a unit cost/duration and the number of units) to develop the estimate. Essentially, a parametric estimate the cost of project, determined by identifying the unit cost or duration and the number of units required for the project or activity. This method is presumed as accurate for traditional assets and linear derivatives but not much accurate for non-linear derivatives.
Monte Carlo simulation: Monte Carlo simulation method produces distributions of possible outcome values. It estimates VaR by simulating random scenarios and revaluing positions in the portfolio to understand the impact of risk and uncertainty in financial, project management, cost, and other forecasting models. Probability distributions are a much more realistic way of describing uncertainty in variables of a risk analysis. This method is considered appropriate for all type of instruments including both linear and non-linear derivatives.
Historical simulation- As its name suggests, the historic simulation method, the historic simulation method takes previously observed events and builds them into a model that predicts the maximum likely loss over the next time period. This method unlike parametric VaR models, does not assume a particular distribution of the asset returns.
