2.2.1
 Probability distribution
Assessing the risk of a single asset requires that
we have some sense for the range of possible outcomes.
For example, a judge sentencing a youthful offender
might consider different scenarios: (1) worst case (pessimistic),
the offender will commit only another minor crime; (2)
expected case (normal), she will commit no more crimes;
(3) best case (optimistic), she will dissuade other
youth from committing crimes. Given this distribution,
what should the judge do? (More
2.2.1>>)
2.2.2  Expected return
What is the expected return when you roll
two dice? Suppose the number you throw represents the
return, and suppose you throw the dice thousands of
times. What would you expect your return to be on average?
We can compute the expected return for each possible
result and then sum these results. (More
2.2.2>>)
2.2.3  Standard deviation (s)
Variability can be measured. That is, risk can be quantified!
The most common measure of risk is the standard
deviation  a numerical measure of the dispersion
around the expected value. Here is how the
standard deviation is calculated for our two dice probability
distributions: (More 2.2.3>>)
2.2.4  Normal distribution
If a dicethrowing distribution were normally distributed
(a classic "bell curve"), a standard deviation
indicates the percentage of likely results around the
mean. Specifically, 38.3% of all returns are within
onehalf standard deviation of the expected return;
68.3% of all returns are within one standard deviation
of the average return, and 95.4% of the returns are
within two standard deviations of the average return.
The larger the standard deviation, the greater the dispersion
and the greater the risk. (More
2.2.4>>)
2.2.5  Coefficient of variation
What happens when there are two distributions with
different expected returns? How do you decide which
distribution involves greater dispersion and thus greater
risk? For example, suppose you are presented with two
investment strategies. (More 2.2.5>>)
