Binomial distribution:

A random experiment with only two possible outcomes categorized as success and failure is called a
Bernoulli trial, where the probability of success 𝑝 is same for each trial.

The probability of failure is denoted by 𝑞 is equal to 1 − 𝑝.

If the probability of success is not the same in each trial, we will not have binomial distribution.

If a coin is tossed once there are only two outcomes {𝐻, 𝑇}

1 1
The probability of obtaining a tail or 𝑞 = 2 and the probability of obtaining a head 𝑝 = 2.

Thus 𝑝 + 𝑞 = 1.

Similarly, if two coins are tossed simultaneously there are four possible outcomes namely
{𝐻𝐻, 𝑇𝑇, 𝑇𝐻, 𝐻𝑇}

The probabilities corresponding to these results are {𝑝𝑝, 𝑞𝑞, 𝑞𝑝, 𝑝𝑞} or 𝑝2 , 𝑞 2 , 2𝑝𝑞 = (𝑝 + 𝑞)2

If three coins are tossed simultaneously there are eight possible outcomes namely

{𝐻𝐻𝐻, 𝑇𝑇𝑇, 𝑇𝑇𝐻, 𝑇𝐻𝑇, 𝐻𝑇𝑇, 𝐻𝐻𝑇, 𝐻𝑇𝐻, 𝑇𝐻𝐻}

The probabilities corresponding to these results are 𝑝3 , 𝑞 3 , 3𝑞 2 𝑝, 3𝑝2 𝑞 = (𝑝 + 𝑞)3

This process is continued for 𝑛 trials and we obtain (𝑞 + 𝑝)𝑛

(𝑞 + 𝑝)𝑛 = 𝑛𝐶0 𝑞𝑛 + 𝑛𝐶1 𝑞𝑛−1 𝑝 + 𝑛𝐶2 𝑞𝑛−2 𝑝2 + ⋯ + 𝑛𝐶𝑛 𝑝𝑛

A discrete random variable X is said to follow binomial distribution if it assumes only non-negative
values and its probability mass function is given by

𝑝(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞𝑛−𝑥 where 𝑥 = 0,1,2, … 𝑛

Here,

𝑝 → probability of success

𝑞 → probability of failure

𝑛 → number of trials
Note: In a binomial distribution

1. 𝑛, the number of trials are finite.

2. All the trials are independent
3. Each trial has only two outcomes usually called success and failures.
4. The probability of success 𝑝 remains constant in each trial.

Example: Suppose a coin is tossed 3 times and we wish to know the probability of getting 2 heads

Possible outcomes are {𝐻𝐻𝐻, 𝑇𝑇𝑇, 𝑇𝑇𝐻, 𝑇𝐻𝑇, 𝐻𝑇𝑇, 𝑯𝑯𝑻, 𝑯𝑻𝑯, 𝑻𝑯𝑯}
3
Thus, the probability of getting 2 heads= 8.

We shall obtain the probability for the same by binomial distribution:

Here the number of trials= 𝑛 = 3.

Number of success (getting two heads) = 𝑥 = 2.

1
Probability of success = 𝑝 = 2.
1
Probability of failure = 𝑞 = 2.

𝑝(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞𝑛−𝑥

1 2 1 3−2 3
𝑃(𝑥 = 2) = 3𝐶2 ( ) ( ) =
2 2 8

Mean and Standard deviation of binomial distribution

𝑛

𝑀𝑒𝑎𝑛 = 𝜇 = 𝐸(𝑋) = ∑ 𝑥𝑝(𝑥)

𝑥=0
𝑛

= ∑ 𝑥 𝑛𝐶𝑥 𝑝 𝑥 𝑞𝑛−𝑥
𝑥=0
𝑛
𝑛!
= 0+∑𝑥 𝑝 𝑥 𝑞𝑛−𝑥
(𝑛 − 𝑥)! 𝑥!
𝑥=1
𝑛
𝑛! 𝑥 𝑥
=∑ 𝑝 𝑥 𝑞𝑛−𝑥 𝑠𝑖𝑛𝑐𝑒 =
(𝑛 − 𝑥)! (𝑥 − 1)! 𝑥! 𝑥(𝑥 − 1)!
𝑥=1
𝑛
𝑛(𝑛 − 1)!
=∑ 𝑝𝑝 𝑥−1 𝑞 𝑛−𝑥
(𝑛 − 𝑥)! (𝑥 − 1)!
𝑥=1
𝑛
(𝑛 − 1)!
= 𝑛𝑝 ∑ 𝑝(𝑥−1) 𝑞(𝑛−1+1−𝑥)
(𝑛 − 1 + 1 + 𝑥)! (𝑥 − 1)!
𝑥=1
 𝑛
(𝑛 − 1)!
= 𝑛𝑝 ∑ 𝑝(𝑥−1) 𝑞(𝑛−1)−(𝑥−1)
[(𝑛 − 1) − (𝑥 − 1)]! (𝑥 − 1)!
𝑥=1
𝑛

= 𝑛𝑝 ∑(𝑛 − 1) 𝐶𝑥−1 𝑝(𝑥−1) 𝑞(𝑛−1)−(𝑥−1)

𝑥=1

= 𝑛𝑝(𝑞 + 𝑝)𝑛−1

= 𝑛𝑝(1)𝑛−1

𝜇 = 𝐸(𝑋) = 𝑛𝑝

Variance

𝑉(𝑋) = 𝜎 2 = 𝐸(𝑋 2 ) − [𝐸(𝑋)]2

𝑛 𝑛
2) 2
𝐸(𝑋 = ∑ 𝑥 𝑝(𝑥) = ∑[𝑥(𝑥 − 1) + 𝑥]𝑝(𝑥)
𝑥=0 𝑥=0
𝑛 𝑛

= ∑ 𝑥(𝑥 − 1)𝑝(𝑥) + ∑ 𝑥𝑝(𝑥)

𝑥=0 𝑥=0
𝑛 𝑛
𝑥 𝑛−𝑥
= ∑ 𝑥(𝑥 − 1) 𝑛𝐶𝑥 𝑝 𝑞 + 𝑛𝑝 𝑠𝑖𝑛𝑐𝑒 𝐸(𝑋) = ∑ 𝑥𝑝(𝑥) = 𝑛𝑝
𝑥=0 𝑥=0
𝑛
𝑛!
= ∑ 𝑥(𝑥 − 1) 𝑝 𝑥 𝑞 𝑛−𝑥 + 𝑛𝑝
(𝑛 − 𝑥)! 𝑥!
𝑥=0
𝑛
𝑛(𝑛 − 1)(𝑛 − 2)! 2 𝑥−2 𝑛−𝑥
=∑ 𝑝 𝑝 𝑞 + 𝑛𝑝
(𝑥 − 2)! (𝑛 − 𝑥)!
𝑥=2
𝑛
2
(𝑛 − 2)!
= 𝑛(𝑛 − 1)𝑝 ∑ 𝑝 𝑥−2 𝑞 𝑛−2+2+𝑥 + 𝑛𝑝
(𝑥 − 2)! (𝑛 − 2 + 2 + 𝑥)!
𝑥=2
𝑛
(𝑛 − 2)!
= 𝑛(𝑛 − 1)𝑝2 ∑ 𝑝 𝑥−2 𝑞(𝑛−2)−(𝑥−2) + 𝑛𝑝
(𝑥 − 2)! [(𝑛 − 2) − (𝑥 − 2)]!
𝑥=2
𝑛

= 𝑛(𝑛 − 1)𝑝 ∑(𝑛 − 2)𝐶𝑥−2 𝑝 𝑥−2 𝑞(𝑛−2)−(𝑥−2) + 𝑛𝑝

2

𝑥=2

𝐸(𝑋 2 ) = 𝑛(𝑛 − 1)𝑝2 (𝑞 + 𝑝)𝑛−2 + 𝑛𝑝

𝐸(𝑋 2 ) = 𝑛(𝑛 − 1)𝑝2 + 𝑛𝑝

∴ 𝑉(𝑋) = 𝑛(𝑛 − 1)𝑝2 + 𝑛𝑝 − (𝑛𝑝)2

𝑉(𝑋) = 𝑛2 𝑝2 − 𝑛𝑝2 + 𝑛𝑝 − 𝑛2 𝑝2
𝑉(𝑋) = 𝑛𝑝 − 𝑛𝑝2
𝑉(𝑋) = 𝑛𝑝(1 − 𝑝)
𝑉(𝑋) = 𝑛𝑝𝑞

Mean of the binomial distribution is 𝑛𝑝

Variance of the binomial distribution is 𝑛𝑝𝑞

Standard deviation of binomial distribution is √𝑛𝑝𝑞

Problems:

1. When a coin is tossed 4 times, find the probability of getting

(i) Exactly one head

(ii) at most 3 heads
(iii) at least 2 heads

Solution: Here 𝑛 = 4

𝑝=probability of getting head = 0.5

𝑞=probability of getting tail = 0.5

Let X be a binomial variate, then 𝑝(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞𝑛−𝑥

4 1
(i) probability of getting exactly one head = 𝑃(𝑥 = 1) = 4𝐶1 (0.5)1 (0.5)4−1 = 4𝐶1 × 0.54 = =
16 4

(ii) probability of getting at most 3 heads = 𝑃(𝑥 ≤ 3)

= 𝑃(𝑥 = 0) + 𝑃(𝑥 = 1) + 𝑃(𝑥 = 2) + 𝑃(𝑥 = 3)

= 4𝐶0 0.50 0.54 + 4𝐶1 (0.5)0.53 + 4𝐶2 (0.5)2 (0.5)2 + 4𝐶3 (0.5)3 0.5
15
= 0.54 (1 + 4 + 6 + 4) =
16
𝑶𝑹
𝑃(𝑥 ≤ 3) = 1 − 𝑃(𝑥 > 3)
= 1 − 𝑃(𝑥 = 4)
15
= 1 − 4𝐶4 0.54 0.50 = 1 − 0.54 =
16
(iii) probability of getting at least 2 heads =𝑃(𝑥 ≥ 2)

= 𝑃(𝑥 = 2) + 𝑃(𝑥 = 3) + 𝑃(𝑥 = 4)

= 4𝐶2 (0.5)2 (0.5)2 + 4𝐶3 (0.5)3 0.5 + 4𝐶4 0.54

11
= 0.54 (6 + 4 + 1) =
16
2. The probability that a pen manufactured by a company will be defective is 0.1. If 12 such pens are
selected, find the probability that

(i) Exactly 2 will be defective

(ii) at least 2 will be defective
(iii) none will be defective

Solution: The probability that a pen is defective is 𝑝 = 0.1

𝑞 = 1 − 𝑝 = 0.9
𝑛 = 12
Let X be a binomial variate, then 𝑝(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞𝑛−𝑥

(i) Probability that exactly 2 pens will be defective=𝑃(𝑥 = 2) = 12𝐶2 (0.1)2 (0.9)10 = 0.2301

(ii) Probability that at least 2 pens will be defective = 𝑃(𝑥 ≥ 2) = 1 − 𝑃(𝑥 < 2)

= 1 − [𝑃(𝑥 = 0) + 𝑃(𝑥 = 1)]

= 1 − [12𝐶0 (0.1)0 (0.9)12 + 12𝐶1 (0.1)(0.9)11 ]

= 1 − [0.2824 + 0.3765]
= 1 − 0.6589 = 0.3410
(iii) Probability that none will be defective = 𝑃(𝑥 = 0) = 12𝐶0 (0.1)0 (0.9)12 = 0.2824

[Link] a large number of parts manufactured by a machine, the mean number of defectives in a sample
of 20 is 2. Out of 1000 such samples, how many would be expected to contain at least 3 defective
parts?
2
Solution: The probability that a part is defective is, from what is given, 𝑝 = 20 = 0.1.

𝑞 = 0.9
𝑛 = 20
𝑝(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞 𝑛−𝑥
The probability function for the distribution is 𝑝(𝑥) = 20𝐶𝑥 (0.1)𝑥 (0.9)𝑛−𝑥

The probability of at least 3 defective samples = 𝑃(𝑥 ≥ 3) = 1 − 𝑃(𝑥 < 3)

= 1 − [𝑃(𝑥 = 0) + 𝑃(𝑥 = 1) + 𝑃(𝑥 = 2)]

= 1 − [20𝐶0 (0.1)0 (0.9)20 + 20𝐶1 (0.1)1 (0.9)19 + 20𝐶2 (0.1)2 (0.9)18 ]

= 0.3233
Hence, out of 1000 samples the expected number of samples that contain at least three defective part
is 0.323 × 1000 = 323.
 2
4. Let 𝑋 be a binomially distributed random variable with mean 2 and SD . Find the corresponding
√3
probability function.

Solution: Mean of the binomial distribution is 𝜇 = 𝑛𝑝

𝑛𝑝 = 2

𝜎 2 = 𝑛𝑝𝑞
2
√𝑛𝑝𝑞 =
√3
4
𝑛𝑝𝑞 =
3
4
2𝑞 =
3
2
𝑞=
3
2 1
𝑝 =1− =
3 3
𝑛𝑝 = 2
1
𝑛( ) = 2
3
𝑛=6

1 𝑥 2 6−𝑥
𝑝(𝑥) = 6𝐶𝑥 ( ) ( )
3 3

5. In a binomial distribution mean is 6 and variance is 1.5.

Find (i) 𝑝(𝑥 = 2) and (ii) 𝑝(𝑥 ≤ 2)

Solution: Given 𝑛𝑝 = 6 and 𝑛𝑝𝑞 = 1.5

6𝑞 = 1.5
𝑞 = 0.25,
𝑝 = 0.75
𝑛𝑝 = 6
0.75𝑛 = 6
𝑛=8

(i) 𝑃(𝑥 = 2) = 8𝐶2 (0.75)2 (0.25)6 = 0.00384

(ii) 𝑃(𝑥 ≤ 2) = 𝑃(𝑥 = 0) + 𝑃(𝑥 = 1) + 𝑃(𝑥 = 2) = 0.0042

6. The probability that a man aged 60 will live to be 70 is 0.65. What is the probability that out of 10
men now aged 60 (i) Exactly 9 will live to be 70 (ii) at most 9 will live to be 70 (iii) at least 7 will live to
be 70.

Solution: 𝑝 = probability that a man aged 60 will live to be 70 is given as 𝑝 = 0.65

𝑞 = 0.35
𝑛 = 10
The probability function for the distribution is 𝑝(𝑥) = 10𝐶𝑥 (0.65)𝑥 (0.35)𝑛−𝑥

i) Probability that exactly 9 will live to be 70 = 𝑃(𝑥 = 9) = 10𝐶9 (0.65)9 (0.35)1 = 0.0725

(ii) Probability that at most 9 will live to be 70 =𝑃(𝑥 ≤ 9)

= 1 − 𝑃(𝑥 > 9) = 1 − [𝑃(𝑥 = 10)] = 1 − 10𝐶10 (0.65)10 (0.35)0 = 0.9866

(iii) Probability that at least 7 will live to be 70= 𝑃(𝑥 ≥ 7)

= 𝑃(𝑥 = 7) + 𝑃(𝑥 = 8) + 𝑃(𝑥 = 9) + 𝑃(𝑥 = 10)

= 10𝐶7 (0.65)7 (0.35)3 + 10𝐶8 (0.65)8 (0.35)2 + 10𝐶9 (0.65)9 (0.35)1 + 10𝐶10 (0.65)10 (0.35)0
= 0.2522 + 0.1757 + 0.0725 + 0.0135
= 0.5138

7. Two persons A and B play a game in which their chances of winning are in the ratio 3:2. If 6 games
are played, find A’s chance of winning at least 3 games.

3
Solution: We note that the probability that A wins a game is 𝑝 =
5

2
𝑞=
5
𝑛=6
Since 6 games are played, the probability function giving 𝑥 successes for A in these 6 games is given
by the binomial probability function

3 𝑥 2 𝑛−𝑥
𝑝(𝑥) = 6𝐶𝑥 ( ) ( )
5 5

The probability of A winning at least 3 games =𝑃(𝑥 ≥ 3) = 1 − 𝑃(𝑥 < 3)

= 1 − [𝑃(𝑥 = 0) + 𝑃(𝑥 = 1) + 𝑃(𝑥 = 2)]

= 1 − [6𝐶0 (0.6)0 (0.4)6 + 6𝐶1 (0.6)1 (0.4)5 + 6𝐶2 (0.6)2 (0.4)4 ]
= 1 − 0.1792
= 0.8208
Thus, A has 82% chance of winning at least 3 games.

8. Four coins are tossed 100 times and the following results were obtained. Fit a binomial
distribution for the data and calculate the theoretical frequencies.

No. of Heads x 0 1 2 3 4
Frequency f 5 29 36 25 5

Solution: 𝑝(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞𝑛−𝑥

Let X denote the number of heads obtained

𝑚𝑒𝑎𝑛 = 𝑛𝑝
∑𝑓𝑥 29 + 72 + 75 + 20
𝑚𝑒𝑎𝑛 = = = 1.96
∑𝑓 100
1.96 = 𝑛𝑝
1.96 = 4𝑝
𝑝 = 0.49
𝑞 = 0.51

Probability function is given by 𝑝(𝑥) = 4𝐶𝑥 (0.49)𝑥 (0.51)4−𝑥

The expected (theoretical) frequency distribution is given by 𝑇𝑥 = 𝑁 × 𝑝(𝑥)

𝑥 = 0, 𝑇0 = 100 × 4𝐶0 (0.49)0 (0.51)4−0 = 6.7652 ≈ 7

𝑥 = 1, 𝑇1 = 100 × 4𝐶1 (0.49)1 (0.51)4−1 = 25.9999 ≈ 26

𝑥 = 2, 𝑇2 = 100 × 4𝐶2 (0.49)2 (0.51)4−2 = 37.4700 ≈ 37

𝑥 = 3, 𝑇3 = 100 × 4𝐶3 (0.49)3 (0.51)4−3 = 24.0004 ≈ 24

𝑥 = 4, 𝑇4 = 100 × 4𝐶4 (0.49)4 (0.51)4−4 = 5.7648 ≈ 6