Next: Transformation Algorithms for Discrete
Up: Transformation of Uniformly Distributed
Previous: Transformation of Uniformly Distributed
  Contents
Inversion Method
- The following property of the generalized inverse can be used as a
basis for the generation of pseudo-random numbers
that can be regarded as realizations of random variables
whose distribution function
is an
arbitrary monotonically nondecreasing and right-continuous
function such that
and
.
- Recall the following auxiliary result.
Theorem 3.4
- Let
be a sequence of independent and uniformly
distributed random variables on
and let
be a
distribution function.
- Then the random variables
where
for
are independent and their distribution function
is given by
.
- Proof
-
- Examples
-
- In the following we discuss some examples illustrating
- how Theorem 3.4 can be used in order to generate
pseudo-random numbers
- that can be regarded as realizations of independent random variables
with a given distribution function
.
- These numbers are also referred to as
-distributed
pseudo-random numbers
,
- in spite of the fact that the empirical distribution function
of the sample
- is only an approximation of
for large
.
- Note that Theorem 3.4 can only be applied directly if
- the generalized inverse
of
is given explicitly (i.e. by
an analytical formula).
- Unfortunately, this situation is merely an exception.
- Exponential distribution
- Let
and
be the distribution function
of the Exp
-distribution, i.e.
- Then
for all
.
- By Theorem 3.4,
- Erlang distribution
- Let
,
and let
be the
distribution function of the Erlang distribution, i.e., of the
-distribution where
 |
(11) |
- Then the generalized inverse
of
cannot be determined
explicitly and therefore Theorem 3.4 cannot be
applied directly.
- However, in Section 1.3.1 of the course ,,Statistik I'' we showed
that
if the random variables
are independent and Exp
-distributed.
- By Theorem 3.4
- Normal distribution
Next: Transformation Algorithms for Discrete
Up: Transformation of Uniformly Distributed
Previous: Transformation of Uniformly Distributed
  Contents
Ursa Pantle
2006-07-20