Calculating Value at Risk Based On A Normal Distribution

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 1

Calculating Value at Risk Based on a Normal Distribution

1.
2.
3.
4.

First youll need to specify several parameters, as illustrated in Figure 1.


The value of your portfolio
Average return for a single time period (this could be over a day, month or year)
Standard deviation of the returns for a single time period
Your desired confidence level

Figure 1

Now perform the calculations as specified in Figure 2

Figure 2

1.
2.
3.

Calculate the minimum expected return with respect to the confidence level (i.e. if your confidence level is 99%, then
youre 99% sure that your return will be above this). This is done with Excels NORM.INV() function.
Calculate the minimum expected return (at the given confidence level)
Now calculate the value at risk for a single time period
You now have your value at risk for a single time period. Lets say that time period is a single day. To convert the value at risk for a
single day to the correspding value for a month, youd simply multiply the value at risk by the square root of the number of
trading days in a month. If there are 22 trading days in a month, then
Value at risk for a month = Value at risk for a day x 22

Limitations and Disadvantages to Value At Risk


There are two major limitations to using VaR as a risk measure.
VaR is not your worst case loss. At a confidence level of 95%, the VaR is your minimum expected loss 5% of the time. Its not
your maximum expected loss. This is the most overlook limitation, can can lead to a false sense of security. The actual loss on
those 5% of trading days may just be a few dollars, or enough to overwhelm your company.
VaR is not necessarily valid when you need it the most. VaR typically assumes that investment returns have a normal
distribution, and the investment behaviour is well-predicted at the tail. But investments tend to be fat-tailed and dont always
follow a normal distribution. So the circumstances VaR was designed for (i.e. events which do not occur often but have a high
impact) are those circumstances in which these assumptions is not valid.
In fact, David Einhorn, president of Greenlight Capital remarked that Value at Risk is an airbag that works all the time, except
when you have a car accident
In summary, Value At Risk should only be be one of several risk measures tools you use.

You might also like