| Core Concept |
| Risk was not quantifiable, attributed to mystical forces
Forces for change: arabic numbers and scholars, impetus of new trade |
| Ancient World |
| No measure of risk, chance was attributed to the Gods. |
|
| Enlightenment |
| 1494: Paccioli Puzzle - how to quantify risk?
Solved by Pascal and Fermat in 1654, laid groundwork for forecasting.
|
|
| Advances |
| The key events in quantitative risk analysis |
| Law of Large Numbers |
| Formulated by Jacob Bernoulli 1703, enables probabilities to be calculated after the fact.
The first attempt to measure uncertainty (jar of pebbles example).
Formed the basis of the insurance industry. |
|
| Normal Distribution |
| Also known as Law of Averages, formulated by Abraham De Moivre 1730.
Data depicted in a bell-curve.
Enabled 'moral certainty' to be determined with fewer samples. |
|
| Decision Theory |
| Formulated by Daniel Bernoulli 1738.
First mathematically expressed utility theory (likelihood * consequences)
Also deals with motivation and future valuation (the Petersburg Paradox)
Basis for theory of supply and demand |
|
| Bayes Theorem |
| Formulated by Thomas Bayes, 1750.
Concerns inverse probability, how new information is used to revise existing probabilities. A important tool for measuring uncertainty. |
|
| Deviation from Mean |
| Formulated by C.F Gauss 1865
Concerns identification of normal data from abnormal data. |
|
|
|
