Three Methodologies for Calculating VaR
There are three major methodologies for calculating VaR.
 Parametric
 Monte Carlo
 Historical
Note that the risk of nonlinear instruments (for example, options) is more complex to estimate than the risk of linear instruments (for example, traditional stocks, bonds, swaps, forwards, and futures), which can be approximated with simple formulas.
Financial instruments are nonlinear when their price does not change by a constant amount given a small movement in an underlying reference asset.
Brief Description
Brief description and use of each approach:
Type  Description  Use 

Parametric  Estimates VaR with equation that specifies parameters (for example, volatility and correlation) as input.  Accurate for traditional assets and linear derivatives, but less accurate for nonlinear derivatives 
Monte Carlo  Estimates VaR by simulating random scenarios and revaluing instruments in the portfolio  Appropriate for all types of instruments, linear or nonlinear 
Historical  Estimates VaR by reliving history; we take actual 
historical rates and revalue a portfolio for each
change in the market  Appropriate for all types of instruments, linear or nonlinear 
Advantages and Disadvantages
Type  Advantages  Disadvantages 

Parametric  Fast and simple to calculate  Less accurate for nonlinear portfolios 
 Monte Carlo 
Accurate for nonlinear instruments
You get a full distribution of potential portfolios (not just a specific percentile)
You can use various distributional assumptions (normal, Tdistribution, and so on)
 Takes a lot of computational power (and hence a
longer time to estimate results)   Historical 
Accurate for nonlinear instruments
You get a full distribution of potential portfolios (not just a specific percentile)
No need to make distributional assumptions

You need a significant amount of daily rate history (at least a year, preferably much more)
You need significant computational power for revaluing the portfolio under each scenario.

From a user's perspective, the important point to remember is that if you have significant nonlinear exposures in your portfolio, a simulation approach will generally be more accurate for estimating VaR than a parametric approximationhowever, at the cost of greater complexity and computational requirements.
Three Approaches
All three approaches for estimating VaR have something to offer and can be used together to get a more robust estimate of VaR. For example, a parametric approach may be used to get an instant snapshot of risks taken during a trading day, while a simulation approach may be used to provide a fuller picture of risks (in particular, nonlinear risks) on a nextday basis.