Biology, images, analysis, design...
Use/Abuse Principles How To Related
"It has long been an axiom of mine that the little things are infinitely the most important" (Sherlock Holmes)

Search this site



Bayes theorem:

Let us assume that, for some event A there are n possible causes, B1 to Bn.
For example, event A could be you finding a stray 100 note.
Event Bi is that note slipping from Bundle 'i'.
You wish to know P(Bi|A), the probability that one of these causes, the ith, resulted in your observed event, A.
(Where P(X|Y) is the probability of randomly selecting X, given Y.)

Each possible cause is mutually-exclusive and non-overlapping.
For each of these causes, the probability of observing A is known.
In other words, if the kth explanation were correct, P(A|Bk) is the probability of observing A.
The probability of each causal event, P(Bi), is also known.
If these causes are equally possible then, given n possible causes, P(Bi)= 1/n, but this is of academic interest, because they cancel out of the equation.
Then the probability that event Bi, resulted in your observed event, A, is:
P(Bi|A) =  P(Bi)P(A|Bi)
  • P(A), is the probability of observing A from any of the bundles, or Σ[P(Bk)P(A|Bk)]