9 — CONTINUOUS DISTRIBUTIONS
[Pages:9]9 -- CONTINUOUS DISTRIBUTIONS
A random variable whose value may fall anywhere in a range of values is a continuous random variable and will be associated with some continuous distribution. Continuous distributions are to discrete distributions as type real is to type int in ML. Many formulae for discrete distributions can be adapted for continuous distributions. Very often, little more is required than the translation of sigma signs into integral signs. The main bad news is that there is no equivalent of probability generating functions.
Adapting the P(X = r) Notation In discussions which involve a single discrete random variable, the notation P(X = r) has been used. When required, mapping is employed to ensure that r N. In discussing a single continuous random variable, X will again be used as the name but x will be used instead of r for the value. In probability theory r strongly implies a non-negative integer whereas x R and may range from - to +. There is at once a problem with the notation P(X = x) for the probability is zero for any particular x. Even if x is constrained to be in some finite range, such as -1 to +1, there are an infinite number of possible values for x. Fortunately, many variants of the P(X = x) notation are still useful. For example:
P(X < 0.5) P(-1 X < +1) P(a X < b)
There is an obvious difficulty with a graphical representation of a continuous random variable. A plot of P(X = x) against x serves no useful purpose! Nevertheless, graphical representations are both possible and useful and here is a first attempt at representing a continuous random variable X which is distributed Uniform(0,2):
X
1 2
?
0
0
1
2
x
It is not immediately clear what label should be attached to the vertical axis but this
representation has the right feel about it. The height of the plot is constant over the range
0 to 2 and is zero outside this range.
The
constant
height
is
1 2
to
ensure
that
the
total
area
under
the
curve
is
1
and
this
is
the
clue to much of what follows. The idea of area corresponding to probability was introduced
on page 1.6 and with continuous random variables area is often the most convenient way
of representing probability.
? 9.1 ?
Probability Density Functions
In
the
present
case,
the
area
under
the
curve
between
x
=
1
and
x
=
1
1 4
is
(1
1 4
-
1)
?
1 2
=
1 8
so the probability P(1
X
<
1
1 4
)
=
1 8
.
In general, this calculation will be an integration and some consideration needs to be given
to the function to be integrated.
The function is called a probability density function or pdf. In the case of a single random
variable it is often named f (x) and this is the appropriate label for the vertical axis:
X
1 2
f (x)
0
0
1
2
x
In the case of the random variable X which is distributed Uniform(0,2):
f (x) =
1 2
,
if 0
x ................
................
In order to avoid copyright disputes, this page is only a partial summary.
To fulfill the demand for quickly locating and searching documents.
It is intelligent file search solution for home and business.
Related download
- continuous probability distributions coconino
- continuous distributions normal distribution in probability theory
- chapter 7 continuous probability distributions examples ksu
- continuous distributions
- lecture 4 random variables and distributions university of washington
- some continuous distributions university of connecticut
- 9 — continuous distributions
- continuous probability distributions university of new mexico
- families of continuous distributions university of arizona
- probability distributions discrete vs continuous ca sri lanka
Related searches
- fidelity fund distributions 2019
- how are annuity distributions taxed
- how are 401k distributions taxed
- vanguard mutual fund distributions 2018
- fidelity year end distributions 2018
- vanguard estimated distributions 2018
- fidelity fund distributions 2018
- vanguard funds distributions 2019
- vanguard year end distributions 2019
- vanguard capital gains distributions 2018
- capital gains distributions taxed
- vanguard year end distributions estimates