Also referred to as
VaR. An application of normal
probability theory and the concepts of duration and
yield volatility can be tied together to provide insight into the
risk of a portfolio or
position. It's the measure of
potential loss from an unlikely, adverse event in a normal
market environment. Specifically, suppose that a manager wants to make the following
statement:
"There is a Y%
probability that the
loss in value from a position will be less than $A in the next T days."
The $A in this statement are popularly referred to as the
Value at
Risk.
The VaR can be exhibited graphically on a
normal distribution curve of a change in the value of a position over the next T days. The VaR would be the
z-score where the area (probability) to the left of that value is equal to 1-Y%.
The general approaches to VaR computation have fallen into three classes called
parametric,
historical simulation, and
Monte Carlo.
Though VaR is very
popular among risk managers these days, no
theory exists to show that VaR is the appropriate measure upon which to build optimal decision rules. VaR does not measure "event" (e.g.,
market crash) risk. That is why portfolio
stress tests are recommended to supplement VaR. VaR does not readily capture liquidity differences among instruments. That is why limits on both tenors and option
greeks are still useful. VaR doesn't readily capture
model risks, which is why model reserves are also necessary.
There's an interesting
paradox involving
VaR and the
Heisenberg Uncertainty Principle. You can predict what sort of
economic crisis will occur next, or you can predict
when it will happen-- but you will never
predict both.