Binomial distribution

Success and failure:

Consider an event associated to a random experiment.
When the random experiment is repeated number of
times, the event may or may not occur in each of those
experiments. The occurrence of the event may be
named ‘success’ and the non-occurrence may be
named as ‘failure’.
For example: 1) In tossing a coin, there are two events,
“Head” and “Tail”. One of the them is a success and the
other is a failure.
2) In throwing a die, we can say, ‘getting a six’ and ‘not
getting a six’ are the two outcomes. One of the them is
a success and the other is a failure.
 Binomial distribution-Meaning
• It is a discrete probability distribution expressing
the probability of one set of dichotomous
alternatives. That is success or failure. It is used
to determine the probability of success in
experiments on which there are only two
equally likely and mutually exclusive outcomes.
 Definition
A random variable X is said to follow binomial
distribution with parameters n and p if the probability
function is :
• P(x)= nCxpxqn-x
• Where X=0,1,2,...,n
• p lies between 0 and 1
• q=1-p or p+q=1
• Where p= probability of success in a single trial, q=1-p,
n=number of trials, x=number of success in ‘n’ trials.
Mean and SD of Binomial Distribution
• Mean=np
• SD(σ) = npq
• Variance=npq
 Situations where Binomial Distribution is applied

Binomial distribution can be applied when:

1) The random experiment has two outcomes
(success or failure)
2) Probability for success in a single trial remains
constant from trial to trial of the experiment.
3) The experiment is repeated finite number of
times.
4) Trials are independent.
Properties of Binomial Distribution
1. It is a discrete probability distribution
2. The shape and location of binomial distribution
changes as ‘p’ changes for a given ‘n’.
3. Binomial distribution has one or two modal values.
4. Mean of the binomial distribution increases as ‘n’
increases with ‘p’ remaining constant.
5. If ‘n’ is large and if neither ‘p’ nor ‘q’ is close to zero,
binomial distribution may be approximated to normal
distribution.
6. Binomial distribution has mean =np and SD = npq
 Qn 1
• Four coins are tossed simultaneously. What is the
probability of obtaining 2 heads exactly.
• Solution
• P(x)= nCxpxqn-x
• n=4, x=2,p=1/2,
• q=1-p = 1/2
• P(2)=4C2x1/22x1/24-2
• =3/8
 Qn 2
• Four coins are tossed simultaneously. What is the
probability of obtaining 3 heads exactly.
• Solution
• P(x)= nCxpxqn-x
• n=4, x=3,p=1/2,
• q=1-p = 1/2
• P(3)=4C3x1/23x1/24-3
• =1/4
 Qn 3
• Probability that a batsman scores a century in a
cricket match is 1/3. Find the probability that out
of 5 matches, he may score century in:
a) Exactly 2 matches
b) No match
c) At least 2 matches
 Solution
P(x)= nCxpxqn-x
n=5, p=1/3, q=1-p = 1-1/3=2/3
a) Exactly 2 matches
P(2)=5C2x(1/3)2x(2/3)5-2
=10x8/243=80/243
b) No matches:
P(0)=5C0x1/30x (2/3)5-0
=1 x 1 x (2/5)5
=32/243
c) At least two matches:
P(2)+P(3)+P(4)+P(5) OR 1-[P(0)+P(1)]
P(0) =5C0x1/30x (2/3)5-0
=1 x 1 x (2/5)5
=32/243
P(1) = 5C1x1/31x (2/3)5-1
= 5x 1/3 x 16/81
=80/243
1-[P(0)+P(1)]=1-[32/243+80/243]
=1-112/243
131/243
 Qn 4
• 8 unbiased coins were tossed simultaneously. Find the
probability of getting
a)Exactly 4 heads
b)No heads at all
c)6 or more heads
d)Utmost two heads
e)Number of heads ranging from 3 to 5
f) At least 1 head
 Ans
a)Exactly 4 heads=70/256
b)No heads at all=1/256
c)6 or more heads=37/256
d)Utmost two heads=37/256
e)Number of heads ranging from 3 to 5=182/256
f) At least one head=1-p(0)=1-1/256=255/256
 Notes
a) A number raised to 0=1
b) nC0 =1
c) nCn =1
d) nC1=n
e) nCx=nCn-x i.e. 8C6=8C2
 Qn 5
• A basket contains 20 bad oranges and 80 good
oranges. Three are drawn at random from this
basket. Find the probability that of three :
a) Exactly two is good oranges
b) At least two is good oranges
c) Utmost two are good oranges.
 Answer
a) Exactly two=0.384
b) At least two is good= 0.896
c) Utmost two are good oranges=0.488
 Qn 6
• Consider families with 4 children each. What
percentage of families would you expect to have:
a) Two boys and two girls
b)At least one boy
c) No girls
d) At the most two girls
Assume equal probabilities for boys and girls.
 Answer
a)Two boys and two girls=3/8= 37.5%
b)At least one boy=15/16=93.75%
c) No girls =1/16=6.25%
d) At the most two girls=11/16=68.75%
 Qn 7
• 4 dice are thrown 162 times. The occurrence
of ‘2 or 3’ is considered a success. In how
many throws, do you expect:
a) Exactly 2 success
b) At least one success
 Answer
a) Exactly 2 success=24/81
(24/81)x162=48
b) At least one success=65/81
(65/81)x162=130
 8
• For a binomial distribution mean=4 and
variance is 12/9. Write down all the terms of
the distribution.
 An
• np=4
• npq=12/9
• q=1/3
• p=2/3
• np=4
• n=4/(2/3)=6.
• Since n= 6, X takes the value of 0,1,2,3,4,5,6.
Therefore, there are seven terms. All the terms
can be obtained from the function P(x)=
nCxpxqn-x taking n=6, p=2/3,q=1/3 and
X=0,1,2,3,4,5,6.
The terms are:
• P(0) =6C0x(2/3)0x (1/3)6-0 =1/729
• P(1) =6C1x(2/3)1x (1/3)6-1 =12/729
• P(2) =6C2x(2/3)2x (1/3)6-2 =60/729
• P(3) =6C3x(2/3)3x (1/3)6-3 =160/729
• P(4) =6C4x(2/3)4x (1/3)6-4 =240/729
• P(5) =6C5x(2/3)5x (1/3)6-5 =192/729
• P(6) =6C6x(2/3)6x (1/3)6-6 =64/729
 9
• In a binomial distribution consisting of 5
independent trials, first and second terms are
0.4096 and 0.2048 respectively. Find the
parameter p and q. Also find 6th term.
n=5
An
P(x)= nCxpxqn-x
First term: P(0)= 5C0p0q5
=1 x 1 x q5 = q5 =0.4096
Second term: P(1)= 5C1p1q4
=5 x p x q4 =0.2048
q/5p=2
q=10p
1-p=10p
1=11p
p=1/11
q=10/11
6th term is P(5)
: P(5)= 5C5p5q0
=0.0000062
 Fitting a binomial distribution
1. Determine the values of p and q and n and
substitute them in the function P(x)= nCxpxqn-x,
we get the probability function of the binomial
distribution.
2. Put x=0,1,2,3... In the function P(x)= nCxpxqn-x ,
we get all the terms.
3. Multiply each such term by N( total frequency)
to obtain the expected frequency.
 Qn 10
Eight coins were tossed together,256 times. Find
the expected frequencies of Heads. Find mean
and SD.
 Answer
• N=256
• n=8
• p=1/2, q=1/2
• Mean=np=8x1/2=4
• SD=Sqrt of npq=8x1/2x1/2=1.414
 P(x)= nCxpxqn-x
An
No of P(X) Expected frequency
heads(X) P(x)x256
0 P(0)= 8C0p(1/2)0(1/2)8 =1/256 (1/256)x256=1
1 P(1)= 8C1p(1/2)1(1/27 =8/256 (8/256)x256=8
2 P(2)= 8C2p(1/2)2(1/2)6 =28/256 (28/256)x256=28
3 P(3)= 8C3p(1/2)3(1/2)5 =56/256 (56/256)x256=56
4 P(4)= 8C4p(1/2)4(1/2)4 =70/256 (70/256)x256=70
5 P(5)= 8C5p(1/2)5(1/2)3 =56/256 (56/256)x256=56
6 P(6)= 8C6p(1/2)6(1/2)2 =28/256 (28/256)x256=28
7 P(7)= 8C7p(1/2)7(1/2)1 =8/256 (8/256)x256=8
8 P(8)= 8C8p(1/2)8(1/2)0 =1/256 (1/256)x256=1
 Qn
The following data show the number of seeds
germination out of 5 damp filter for 80 sets of
seeds. Fit a binomial distribution of this data
and find the expected
x 0 1 2 3 4 5
f 6 20 28 12 8 6
•
An
Since ‘p’ is not given find mean of the given data.
X f fx
0 6 0
1 20 20
2 28 56
• Mean(np)= Ʃfx/N=174/80=2.175 3 12 36
• n=5 4 8 32
• P=2.175/5=0.435 5 6 30
80 174
• Q=0.565
 An
x P(X) Expected frequency
P(x)x80
0 P(x)= nCxpxqn-x 5
1 P(x)= nCxpxqn-x 18
2 P(x)= nCxpxqn-x 27
3 P(x)= nCxpxqn-x 21
4 P(x)= nCxpxqn-x 8
5 P(x)= nCxpxqn-x 1