Binomial Distribution

Let there be n independent trials; each of which has only two outcomes, success (S) and
failure (F) with probability p and q, respectively. The probability that there will be r
successes in n trials is given by P( X = r )= nCr p r q n−r ; r = 0,1, 2, ..., n.

Where p is the probability of success and q=1-p is the probability of failure. This is a discrete
distribution.

The following conditions must be satisfied for the binomial distribution:

1) There should be a fixed number of trials i.e. n is fixed.

2) The trials are independent.

3) There are only two outcomes for each trial.

4) The probability of success (p) and the probability of failure (1-p=q) remains same or
constant from trial to trial.

Remarks

i) The probability function satisfies the conditions:

a) P(x )=nCx p x q n−x  0; for x = 0,1, 2, ..., n.

n n

 P(x = r ) =  nCr p r q n−r = q n + nC1 p1q n−1 + nC2 p 2q n−2 + ... + p n = (q + p ) = 1  p + q = 1

n
b)
r =0 r =0

ii) The two independent constants n and p of the distribution are known as parameters of the
distribution.

1
iii) If p = q = , then the binomial distribution is symmetric otherwise it is skewed.
2

Examples

1. An insurance salesman contacts ten different families. The outcome associated with
visiting each family can be referred to as a success if the family purchases an insurance
policy and a failure, if not. If the probability of selling a policy is assumed to be the same for
each family and the decision to purchase a policy or not by one family is not influenced by
the decision of any other family, then we have a situation analogous to the binomial
experiment.

2. An experiment consists in selecting five radios at random from a lot and inspecting then
classifying them as defective and non-defective. A defective radio is labeled as a success,
while a non-defective radio is labeled as a failure. Suppose 20% of the radios are defective. If
this probability is assumed to remain constant from trial to trial, then X, the number of
Page 1 of 3
successes is a binomial random variable assuming the values 0, 1, 2, 3, 4 and 5. Clearly the
experiment is a binomial experiment with n=5 and p=0.20.

Mean
n n n
n! n
n(n − 1)!
E (x ) =  x  p(x ) =  xn C x p x q n− x =  x  p x q n− x =  x  p x q n− x
x =0 x =0 x =0 x!(n − x )! x =0 x(x − 1)!(n − x )!

= np
n
(n − 1)! p x−1q n− x = np n−1C p x−1q n− x = np(q + p )n−1 = np
n
 p + q = 1
x =1 ( x − 1)!(n − x )!

x =1
x −1

Variance

( )
V (x ) = E x 2 − E ( x ) = Ex(x − 1) + x − E (x ) = Ex(x − 1) + E (x ) − E (x )
2 2 2

= Ex(x − 1) + np − n 2 p 2

n n n
n!
Ex(x − 1) =  x(x − 1)  p(x ) =  x(x − 1)n C x p x q n− x =  x(x − 1)  p x q n− x
x =0 x =0 x =0 x!(n − x )!
n
n(n − 1)(n − 2)! n
(n − 2)! p x−2 q n− x
=  x(x − 1)  p x q n− x = n(n − 1) p 2 
x =0 x(x − 1)(x − 2)!(n − x )! x = 2 ( x − 2 )!(n − x )!
n
= n(n − 1) p 2  n−2C x−2 p x−2 q n− x = n(n − 1) p 2 (q + p )
n−2
= n(n − 1) p 2  p + q = 1
x =2

 V (x ) = n(n − 1) p 2 + np − n 2 p 2 = n 2 p 2 − np2 + np − n 2 p 2 = np(1 − p ) = npq.

Ex. 1. Eight unbiased coins are tossed. Find the probability of getting (i) 4 heads, (ii) at least
2 heads, (iii) at best 3 heads.

1
Sol. Let X be the number of heads. Since coins are unbiased, P(H ) = P(T ) = .
2
x 8− x 8
1 1 1
The probability function of X is P( X = x )=8Cx     =8Cx   for x = 0,1, 2, ...,8.
2 2 2
8 8 8 8
1 8!  1  8  7  6  5  4!  1  1 35
(i) P( X = 4)= C4   = 8
  =   = 70    =
 2  4!4!  2  4  3  2 1  4!  2   2  128

(ii) P( X  2 ) = 1 − P( X  2 ) = 1 − P( X = 0 ) + P( X = 1)

 8  1 8 8  1 8    1 8 1 
8
1
8
9 247
= 1 −  C0   + C1    = 1 − 1    + 8     = 1 − 9    = 1 − = .
  2   2     2   2   2 256 256

(iii) P( X  3) = P( X = 0 ) + P( X = 1) + P( X = 2 ) + P( X = 3)
Page 2 of 3
 8 8 8 8 8
1 1 1 1  8! 8!  1 
=8C0   +8C1   +8C2   +8C3   = 1 + 8 + +  
2 2 2 2  2!6! 3!5!  2 

8 8
 8  7  6! 8  7  6  5!  1  1 93
= 9 + +   = (9 + 28 + 56 )  = .
 2 1  6! 3  2 1  5!  2   2  256

Ex. 2. A company produces electric bulbs. Ten percent of the produced bulbs are usually
found defective. Six bulbs are randomly selected from a day’s output. Find the probability
that, out of 6 bulbs (i) one bulb is defective, (ii) at least 1 bulb is defective, (iii) at best 1 bulb
is defective.

Sol. Let X be the number of defective bulbs. The probability of a defective bulb is p=0.1.
Therefore, the probability function of X is given by

P( X = x )=6Cx ( p ) (q ) =6Cx (0.1) (0.9)

x 6− x x 6− x
for x = 0,1, 2, ..., 6.

(i) P( X = 1)=6C1 (0.1) (0.9) = 0.35429

1 5

(ii) P( X  1) = 1 − P( X  1) = 1 − P( X = 0) = 1−6C0 (0.1) (0.9) = 0.46856

0 6

(iii) P( X  1) = P( X = 0) + P( X = 1)= 6C0 (0.1) (0.9) + 6C1 (0.1) (0.9)

0 6 1 5

= 0.53144 + 0.35429 = 0.88574 .

Page 3 of 3