A way of expressing the variation in potential outcomes based on the size
of the sample. The risk decreases as the sample size increases. For example,
loss forecasts rely on historical loss data. Increased amounts of credible loss
information reduce the amount of process risk inherent in the calculation. In
insurance terminology, the law of large numbers is directly related to the credibility
of the loss predictions on which premiums are based. The risk decreases as the
number of exposure units increases.