1

Module 3: Random Variables

Lecture 2: Probability Distribution of Random Variables

Probability Distribution of a Random variable
Probability distribution of a Random Variable (RV) is a function that provides a complete
description of all possible values that the RV can take along with their probabilities over the
range of minimum and maximum possible values (in a statistical sense) of that RV.
Probability Distribution of a discrete random variable
Probability distribution of a discrete random variable specifies the probability of each possible
value of the random variable. Being probabilities, the distribution functions of discrete random
variables are concentrated as a mass for a particular value, and generally known as Probability
Mass Function (PMF). In figure 1, the PMF of a discrete random variable X is plotted against
different possible values i.e, x. Thus, the Probability Mass Function (PMF) is the probability
distribution of a discrete random variable and generally denoted by p
x
(x). It indicates the
probability of the value X = x taken by X.
Properties of PMF
The properties of PMF are:
- ( ) X all for x p
X
0 >
- ( ) 1 =

x p
X

It may be noted that if in a particular case, it is certain that the outcome is only c, then
( ) | | 1 p c P X c
X
= = = . In the case of mutually exclusive outcomes,
, , ......
1 2
x x x
n
,
( ) ( ) ( ) ( ) ... ...
1 2 1 2
p x x x p x p x p x
n n
X X X
= + + + .

Example problem of PMF
Prob. The number of floods recorded per year at a gauging station in Italy are given in the Table
1. Find the PMF and plot it. (Kottegoda and Rosso, 2008)
2

Table 1: Number of flood occurrences per year from 1939 to 1972

Number of floods in a
year
Number of occurrences
Number of floods
in a year
Number of
occurrences
0 0 5 4
1 2 6 1
2 6 7 4
3 7 8 1
4 9 9 0

Soln. Total number of floods is 34.
Let X denote the number of occurrence of flood. The probabilities for different number of floods
can be obtained as follows.
( ) ( ) ( ) ( ) ( ) ( )
2 6 7 9 4
0 0; 1 ; 2 ; 3 ; 4 ; 5 ;
34 34 34 34 34
p X p X p X p X p X p X
X X X X X X
= = = = = = = = = = = =
( ) ( )
1 4 1
6 ; 0; 8 ;
34 34 34
p X p X p X
X X X
= = = = = =
| |
|
\ .


and ( ) 0 9 p x for al x
X
= >
The obtained PMF are plotted in the Fig. 1.

Fig. 1. Probability Mass Function (PMF) of flood occurrences X
per year at the gauging station
3

Some standard Probability Mass Functions (PMFs)

Some standard PMFs are:
- Binomial Distribution
- Multinomial Distribution
- Negative Binomial Distribution
- Geometric Distribution
- Hypergeometric Distribution
- Poisson Distribution
These distributions will be discussed in subsequent lectures.
Probability Distribution of a continuous random variable
Probability distribution of a continuous random variable specifies continuous distribution of
probability over the entire feasible range of the random variable. In contrast to the discrete
random variable, the probability of a continuous random variable is distributed over the entire
range of the RV and at a particular value the magnitude of the distribution function can be
treated as density. In physics, density functions can be integrated to obtain mass; similarly
probability density functions can be integrated to obtain probabilities. Hence, the distribution
function of continuous random variables is generally known as probability density function
(pdf).
Thus, A Probability Density Function (pdf) is the probability distribution of a continuous random
variable. It is conventionally denoted by ( ) x f
X
. In figure 2, the pdf of a continuous random
variable X is plotted against x.

Fig. 2 Probability Density Function (pdf) of a continuous random variable X


4

Conditions for valid pdf

The conditions for a valid pdf are
1. The pdf is a continuous nonnegative function for all possible values of x.
( ) 0 f x for all X
X
>
2. The total area bounded by the curve and the x axis is equal to 1. In figure 3, the shaded
area under the curve is equal to 1.
( ) 1 f x dx
X

=
}

Fig. 3 Probability Density Function (pdf) of X
It may be noted that when a pdf is graphically portrayed, the area under the curve between two
limits, x
1
and x
2
(such that x
2
>
x
1

) gives the probability that the random variable X lies in the
interval x
1
to x
2
. In figure 4, the shaded portion gives the probability of the random variable X
lying in the interval
1
x to x
2

.

( ) ( ) ( )
1 2
2
1
1 1
x
P x X x f x dx
X
x
s s = s
}

5

Fig. 4 Probability Density Function (pdf) of X

Example problem on pdf
Prob. (Ang and Tang,1975) A random variable X has a pdf of the form
( )
elsewhere
x x x f
X
0
10 0
2
=
s s =o

(a) Under what condition is this function a valid pdf ?
(b) What is the probability of X being greater than 5?
Solution:
(a) To satisfy all properties of pdf,
1000
3
,
1
3
,
1
10
0
3
10
0
2
=
=
(

=
}
o
o
o
or
x
or
dx x

(b) Now the probability
( ) ( ) 875 . 0
1000
5
1
1000
3
1 5 1 5
3
5
0
2
= = = s = >
}
dx
x
X P X P

6

Some standard probability distribution functions (pdfs)

Normal or Gaussian Distribution
Normal Distribution is a continuous probability distribution function with parameters (mean)
and
2
(variance) and its probability density function can be expressed as:
( )
( )
< < =

x for e x f
x
X
2
2
2
2
2
1
o

to

Figure 5 shows 3 normal distribution functions with different parameters.

Fig. 5 Normal distribution functions
Exponential Distribution
Exponential Distribution is the probability distribution function with parameter , and its
probability density function is expressed as:

( )
otherwise
x for e x f
x
X
0
0
=
> =

Figure 6 shows 3 exponential distribution functions with different parameters.
( ) x f
X
x
7

Fig. 6 Exponential distribution functions
Gamma Distribution
Gamma distribution is the probability distribution function with parameters and (where >0,
>0) and its probability density function is expressed as,
( )
( )
otherwise
x for e
x
x f
x
X
0
0
/
1
=
>
I
=

|
o
o
| o
where ( )
}

= I
0
1
dx e x
x o
o
When is an positive integer, ( ) ( )! 1 = I o o
Figure 7 shows 3 gamma distribution functions with different parameters.

8

Fig. 7 Gamma distribution functions