Continuous Probability

Distribution
A continuous probability distribution is
a distribution which cannot be given in
tabular form because since the
variable is continuous, it has zero
probability of exactly assuming its
values. This type of probability
distribution deals with intervals rather
than point values. It uses a formula
and could be graphed as a continuous
curve.
Problem:

A continuous random variable X that

can assume values between x = 2 and
x = 5 has a density function given by
21  x 
f ( x) 
27

a) Find P(X < 4)

b) Find P(3< X < 4)
 21  x 
f ( x) 
27
x = 2, 3, 4, 5

2(1  2) 6 2(1  4) 10
f (2) =  f (4) = 
27 27 27 27

2(1  3) 8 2(1  5) 12
f (3) =  f (5) = 
27 27 27 27
 Probability Graph

f(x)

x
 1 6 10 16
P (x  4)  ( )(2)(  ) 
2 27 27 27
 1 8 10 9
P (3  x  4)  ( )(1)(  ) 
2 27 27 27
Problem
w
Problem
w
Problem
w
Joint Probability Distribution

A table or formula listing all possible

values of x and y of the discrete
random variables X and Y, together
with the associated probabilities
f(x,y) is called a joint probability
distribution.
 Marginal Distribution

Refers to the one dimensional

probability distribution of X alone,
with values g(x) or Y alone with
values h(y).
 Conditional Distribution

Conditional distribution of the

discrete random variable Y, given
that X = x is given by:

 y  f ( x, y )
f  
 x g ( x)

g(x) > 0
Interdependent Random Variables

The random variables X and Y are

said to be statistically independent if
and only if f(x,y) = g(x) h(y) for all
possible values of X and Y.
Problem:

Two refills for a ball point pen are

selected at random from a box that
contains 3 blue refills, 2 red refills
and 3 green refills. If X is the
number of blue refills, Y is the
number of red refills selected, find:
a) the joint probability function f(x,y)

b) the marginal distributions of X and Y

c) conditional distribution f ( x 1 ) for all

values of x and determine P ( X  0 Y  1)
d) are random variables X and Y
statistically independent?
Solution:
a) joint probability function f (x, y)
X = blue refill (3)
Y = red refill (2)
Z = green refill (3)

Computing for the total number of

possible outcomes:
nS = C(8,2) = 28
The possible pairs of values (x, y):

(x, y) = (0,0), (0,1), (0,2), (1,0), (1,1), (2,0)

Computing for the probabilities of the

possible pairs of values (x, y):

f ( x, y ) 
  
X
x  Y
y
Z
z

nS
f ( x, y ) 
X
x Y
y  Z
z

nS

f (0,0) 
  
3
0
2
0
3
2

3
28 28

f (0,1) 

3
0
2
1
3
1

6
28 28

f (0,2) 
   
3
0
2
2
3
0

1
28 28
f ( x, y ) 

X
x Y
y  Z
z

nS

f (1,0) 
 
3
1
2
0
3
1

9
28 28

f (1,1) 
  
3
1
2
1
3
0

6
28 28

f ( 2,0) 
   
3
2
2
0
3
0

3
28 28
Joint Probability Distribution:
X
f(x,y)
0 1 2
3 9 3 15
0
28 28 28 28
6 6 12
Y 1
28 28 28
1 1
2
28 28

1
10 15 3
28 28 28
b) the marginal distributions of X and Y

Marginal Distribution of X

x 0 1 2
10 15 3
g(x)
28 28 28
Marginal Distribution of Y

y 0 1 2
15 12 1
h(y)
28 28 28
c) conditional distribution f ( x ) for all
1
values of x and determine P ( X 0 )
Y 1

f ( x , y )
f(x ) ; h(y) > 0
y h( y )

x f ( x,1)
f( )
1 h(1)
Solving for h(1):

h(1) = f(0, 1) + f(1, 1)

6 6 12 3
h(1) =   
28 28 28 7

x f ( x ,1)
f( )
1 3
7
7
f ( x )  f ( x,1)
1 3
 x 7
f ( )  f ( x,1)
1 3
when x = 0:
0 7 7 6 1
f ( )  f (0,1)  ( ) 
1 3 3 28 2
when x = 1:
1 7 7 6 1
f ( )  f (1,1)  ( ) 
1 3 3 28 2
when x = 2:
2 7 7
f ( )  f ( 2,1)  (0)
1 0
3 3
Therefore the conditional distribution
f ( x ) for all values of x is:
1

x 0 1 2
1 1
f (x ) 0
1 2 2
To find P ( X  0 Y  1)

f ( 0 )
P( X  0 ) 
1
Y 1
1
P( X  0 )
Y 1 2
d) are random variables X and Y
statistically independent?

for statistically independent events,

f(x,y) = g(x)h(y)

consider point (0,1)

f(0,1) = g(0) h(1)
6  10   12 
28
   
 28   28 

Hence, X and Y are not

statistically independent.
 The Mean

The mean of a random variable can

be interpreted as the mean of the
population or distribution whose
observations are all the values of X
that are generated by repeating the
experiment over and over again
indefinitely.
 It is also called mathematical
expectation or expected value.

It can be computed using the formula:

n
  E ( X )   xi f ( xi )
i 1
 If X is a discrete random variable
with the probability distribution given
by P(X=x) where x = x1, x2, ...xn. The
mean of the random variable g(X) is:

n
 g ( X )  E[ g ( X )]   g ( xi ) f ( xi )
i 1
 If X and Y are discrete random
variables with the joint probabilities
given by f(x,y) where x = x1, x2, ...xm and
y = y1, y2, …yn .The mean of the random
variable g(X,Y) is:

m n
 g ( X ,Y )  E[ g ( X , Y )]    g(x y ) f (x , y )
i i i i
i 1 i 1
Problem:

Let X be a random variable with the

following probability distribution. Find
the mean of X.

X 0 1 2 3
8 4 2 1
P( X  x)
27 9 9 27
Solution:

X 0 1 2 3
8 4 2 1
P( X  x)
27 9 9 27
n
  E ( X )   xi f ( xi )
i 1

 x  E ( X )  0278   1 94   2 92   3 271 
x  E( X )  1
Problem:

In a gambling game, a man is paid

$5 if he gets all heads or tails when 3
coins are tossed and he pays $3 if
either 1 or 2 heads show. What is his
expected gain?
Solution:

nS = 2 x 2 x 2 = 8

2 6
p (W )  p ( L) 
8 8

E ( X )  $5 82   $3 86   $1

Gambler on the
average will lose $1
per toss of the 3 coins
 For the joint probability distribution shown
below, find the expected value of g(X,Y) = XY.
Also find x and y.
X
f(x,y)
0 1 2
3 9 3 15
0 28 28 28 28
6 6 12
Y 1 28 28 28
1 1
2
28 28

10
28
15
28
3
28 1
Solution: Solving for  g ( X ,Y )
2 2
 g ( X ,Y )    g ( xy) f ( x, y)
x 0 y 0

 g ( X ,Y )  0  0  f 0,0  0 1 f 0,1

 (0) ( 2) f (0,2)  (1) (0) f (1,0)
 (1) (1) f (1,1)  (2) (0) f (2,0)
 g ( X ,Y )  0  0  0  0  (1) (1)  6   0
 28 
 g ( X ,Y )  6
28
Solving for  ( X )
2
 ( X )   x g ( x)
x 0

 ( X )  0  g 0  1 g 1  (2) g (2)

 10 
 ( X )  (0)   (1)  15   (2)  3 
 28   28   28 
( X )  21
28
Solving for  (Y )
2
 (Y )   y h ( y )
y 0

 (Y )  0  h0   1 h1  (2) h(2)

 15 
 (Y )  (0)   (1)  12   (2)  1 
 28   28   28 
14
 (Y ) 
28
Variance
The variance of a random variable can be interpreted as the
variance of the population or distribution whose observations
are all the values of X that are generated by repeating the
experiment over and over again indefinitely. It can be
computed using the formula:

n
 2  E[( X   ) 2 ]   ( xi   ) 2 f ( xi )
i 1
If X is a discrete random variable with
the probability distribution given by
f(X), the variance of the random
variable X is:

n
 2
g ( x)  E{[ g ( X )   g ( x ) ] }   [ g ( xi )   g ( X ) ]2 f ( xi )
2

i 1
Problem:

Find  of 2, 5, 5, 8, 8, 8.
2

x x ( x   )2
2 -4 16   x
N
5 -1
5 -1 36
 6
8 2 4 6
8 2 4
8 2 4

 x  36
 x   2 1 4 16

2 3 1
Px   
2

6 6 6

n
 2   ( xi   ) 2 f ( xi )
i 1

 2  (1)  2   4  3   16  1 

6 6 6
2 5
Problem:
Find the expected number of boys
in a committee of 3 selected at
random from 4 boys and 3 girls.
What is the variance of this
expected number of boys?
Solution:

x = no. of boys

y = no. of girls

nS = C(7,3) = 35

  
X
x
Y
y
f(x) =
nS
 f(x) =
  
4
x
3
3 x
for x = 0, 1, 2, 3
35
f ( 0) 
4
0 3
3

1 f ( 2)  4
2  
3
1 
18
35
35 35 35

 
4
1   3
12
2
4
3 4
3
0
f (1)   f (3)  35
35 35 35
 3

To find the MEAN:  ( X )   x f ( x)

x 0

 ( X )  0  f 0  1 f 1  (2) f (2)  (3) f (3)

 ( X ) (0) 1
 (1)  12   ( 2)  18   (3)  4 
      
 35   35   35  35 

 ( X )  12
7
 3

To find the VARIANCE:    ( x   ) f ( x)

2 2

x 0

2 2
 12   1   12   12 
   0      1    
2

 7   35   7   35 
2 2
 12   18   12   4 
  2      3    
 7   35   7   35 

  0.49
2
Problem:

Let X be a random variable with the

following probability distribution. Find
the standard deviation of the random
variable g(X) =(2X + 1)2.

X -3 6 9
1 1 1
P( X  x)
6 2 3
Solution: To find the MEAN:
9
 ( 2 X 1)   (2 X  1) 2 f ( x)
2
x 3

X -3 6 9
1 1 1
P( X  x)
6 2 3

 ( 2 X 1)  1
 2 3  1    26   1 2  1 
2
2

6 2
21
 29   1  
 3
 ( 2 X 1)  209 2
To find the  2  n [ g ( x )   ]2 f ( x )
VARIANCE:
g ( x) 
i 1
i g(X ) i

n
 (22 X 1)   [(2 X  1) 2   ( 2 X 1) ]2 f (2 X  1) 2
2 2
i 1
1
 2
( 2 X 1) 2  2

 2 3  1  209  
6
2

2 1 
 
 26  1  209  2 
2
 

 1
 29  1  209  
2
2

 3
 2
( 2 X 1) 2  14144

  2

  14144
  118 .93