A Bernoulli process is characterized by
a probability of success, to which
is associated the uncertain number ,
and probability of failure,
to which is associated the uncertain number .
Therefore, technically, a Bernoulli distribution
is just a binomial with . But conceptually
it is very important, because it is the basic
process from which other distributions arise:
- a binomial distribution describes the probability
of the total number of
successes in independent Bernoulli trials
`having' (or more precisely `believed to have')
the same probability of success ;
- a geometric distribution describes the
probability (again assuming independence and constant )
of the trial
at which36 the first success occurs;
- a Pascal distribution (or negative binomial
distribution)
concerns finally the
trial at which the -th success occurs.37