Binomial Distribution

Success and Failure in an Experiment

There are certain kinds of experiments which have two possible outcomes, one of these two
outcomes is called a success and the other is called a failure. For example, in tossing a coin,
we get a head or tail. If getting head is taken as a success, then getting tail is a failure.
Random Variable
We know that tossing of a coin, throwing a die, drawing a card from a pack of 52 cards etc.,
are all experiments. If a coin is tossed either head or tail turns up and the chance of getting head
1
and tail are exactly 50% it means the probability in each case is . Similarly, a die is cast the
2
1
possible outcomes are 1,2,3,4,5,6 each of which occurs with the probability .
6
The experiments whose results or outcomes depend on chance are called random experiments.
The definition of a random variable depends on random experiment.
“A variable whose numerical value is determined by the outcome or result of a random
experiment is called a random variable”. A random variable is also known as a chance variable
or stochastic variable.
For example; Consider a random experiment of tossing a coin. Then the sample space
S = {H,T}. Let X be a random variable which denoted the number of heads observed. Then X
= 0 if the outcome is T, and X = 1 if the outcome is H so X= {0,1}.
Consider a random experiment of tossing a coin twice. Then the sample space
S = {HH, HT, TH, TT}. Let X be a random variable which denoted the number of heads
observed. Then X = 0 if the outcome is TT, and X = 1 if the outcome is HT or TH and X=2 if
outcome is HH so X= {0,1,2}
For example; Consider a random experiment of tossing a coin three times or three coins are
tossed once. Then the sample space S = {HHH, HHT, HTH, HTT, THH, THT, TTH, TTT}.
Let X be a random variable which denoted the number of heads observed. Then X = 0 if the
outcome is TTT, and X = 1 if the outcome is HHT or THT or TTH, X = 2 if the outcome is
HHT or HTH or THH and finally X = 3 if the outcome is HHH. X is a random variable whose
values are determined by the outcomes of a random experiment of tossing a coin three times
and it is a function with domain S and range {1, 2, 3}. We can also represent the random
variable in the form of a function as follows:
consider a real valued function X on S defined by X : S  R such that X (w) = number of
heads observed, for all w in S. Then X is a random variable such that; X(TTT) = 0, X(THT) =
1, X(HTT) =1, X(HTT) = 1, X(THH) = 2, X(HTH) = 2, X(HTT) = 2, X(HHH) =3.
A random variable may either discrete or continuous. If a variable can assume only a discrete
set of values i.e. a finite set of values or at most an innumerably infinite set of values, then it is
called a discrete random variable. The number appearing on top of a die when it is cast, the
number of defectives in a sample of electric bulbs, the number of printing mistakes per page of
a book, the number of telephone call received per day are examples of a discrete random
variable. On the other hand, if a variable can assume all real values at a given interval, it is
called a continuous random variable. In this case no enumeration of favorable and total cases
is possible. Heights, weights, temperature, time etc. are examples of continuous random
variables.
Probability Function of a Random Variable
If a random variable X assumes the discrete set of values x1, x2 , x3.........., xn then the function
f defined by f ( xi )  p( X  xi ) = Probability that X assumes the value xi is called Probability
Function ( or Density Function or Probability Mass Function) of X. This function gives the
probabilities corresponding to different values x1 , x2 , x3 .........., xn of the variable X and
satisfies the following two conditions:
(i) f ( xi )  0, for some i  1,2,3,........n (ii)  f (x )  1
i

Discrete Probability Distribution of a Random Variable

A description giving the values of a random variable along with the corresponding probabilities
is called the probability distribution of the random variable.
If a random variable X can assume a discrete set of values x1 , x2 , x3 .........., xn with their
corresponding probabilities p1 , p2 , p3 .........., pn where p1  p2  p3  ..........  pn  1 then the
probability distribution of X is given by

X x1 x2 x3 …………… xn
p(X) p1 p2 p3 …………… pn
Bernoulli’s Theorem
Let there are n independent trials in an experiment and let the random variable X denotes the
number of success in these trials. Let the probability of getting a success in a single trial be p
and that of getting a failure be q so that p  q  1 . Then
( nr )
p( X  r ) = Cr p q
n r

Proof. Let us denote success by S and failure by F.

n
The number of ways of getting r success in n trials = Cr

p( X  r ) = Cr p[{SSS........S} (r times) and {FFF ..........F} (n-r) times]

n

n
= Cr [{ p(S ). p(S ). p(S )........ p(S )} (r times)
 { p( F ). p( F ). p( F ).......... p( F )} (n-r) times]
n
= Cr { p. p. p..... p} (r times)  {q.q.q............q} (n-r) times
n r ( nr )
= Cr p q .
n1
Remark. We have, p( X  0)  q , p( X  1)  npq , p(X  2)  nC2 p 2 q (n  2) etc.
n

The probability distribution of X may be expressed as follows:

X : 0 1 2 ………….. r
n n 1 n 2 ( n 2 ) n r ( nr )
p(X ) : q npq C2 p q ………. Cr p q
This distribution is called a Binomial Distribution.
Conditions for Applicability of Binomial Distribution
(i) The experiment is performed for a finite and fixed number of trials.
(ii) Each trial must give either a success or failure
(iii) The probability of a success in each trial is remains constant and does not change from
trial to trial.
(iv) The trials are independent that is the probability of an event in any trial is not affected
by the results of any other trial.
Properties of Binomial Distribution
(i) Binomial Distribution is a Discrete Probability Distribution in which the random
variable X assumes the values 0,1,2,3,...., n , where n is finite.
q p
(ii) Mean = np , variance  npq , Standard Deviation npq , Skewness  and
npq
(1  6 pq)
Kurtosis  where q  1  p.
npq
(iii) The mod of Binomial Distribution is that value of X which occurs with the largest
probability. It may have either one or two modes.
(iv) If two independent random variables X and Y follow Binomial Distribution with
parameters (n1 , p) and (n2 , p) respectively then their sum X+Y also follows Binomial
Distribution with the parameters (n1  n2 , p) .
Example 1 (a) A coin is tossed 4 times. If X is the number of heads observed, find the
probability distribution of X.
Solution (a) When a coin is tossed, we have S = {H, T}
1 1 1
p(getting a head) =  p and p(not getting a head) = 1    q
2 2 2
Let X be the random variable denoting the number of heads. In 4 trials, we may get 0 or 1 or 2
or 3 or 4 heads. So, X may assume the values 0,1,2,3,4.
0 ( 4 0 ) 1 ( 41)
1 1 1 1 1 1
p(X  0)  C0      . , p(X  1)  C1      .
4 4

2 2 16 2 2 4

2 ( 4 2 ) 3 ( 43)
1 1 3 1 1 1
p(X  2)  C2      . , p(X  3)  C3      .
4 4

2 2 8 2 2 4

4 ( 4 4 )
1 1 1
p(X  4)  C4     
4
.
2 2 16
Hence, the required probability distribution is given by
X 0 1 2 3 4
p(X ) 1 1 3 1 1
16 4 8 4 16
(b) Find the probability distribution of number of sixes in three tosses of a die.
Solution. When a die is tossed the sample space S = {1, 2, 3, 4, 5, 6}
1 1 5
The probability of getting a six, p = and probability of not getting a six, q = 1   .
6 6 6
Let X be the random variable denoting the number of sixes. In 3 trials the number of sixes may
be 0 or 1 or 2 or 3. So, X may assume the values 0, 1, 2, 3.
0 ( 30 ) 1 ( 31)
1 5 125 1 5 25
p(X  0)  C0      p(X  1)  C1   
3 3
.,   .
6 6 216 6 6 72
2 ( 32 ) 3 ( 33)
1 5 5 1 5 1
p(X  2)  C2      . , p(X  3)  C3     
3 3
.
6 6 72 6 6 216
Hence, the required probability distribution of X is given by

X 0 1 2 3

p(X ) 125 25 5 1
216 72 72 216

(c) Find the probability distribution of the number of doublets in 4 throws of a pair of dice.
Solution. When a pair of dice is thrown, there are 36 possible outcomes. All possible outcomes
are (1, 1), (2, 2), (3, 3), (4, 4), (5, 5), (6, 6)
6 1 1 5
Then, p(doublet) p   , q  1  .
36 6 6 6
Let X denotes the number of doublets. In 4 throws, we can have 0 or 1 or 2 or 3 or 4 doublets.
0 4 1 3
1 5 625  1   5  125
p(X  0)  C0      p(X  1)  C1     
4 4
., .
 6   6  1296  6   6  324
2 2 3 11
1 5 25 1 5 5
p(X  2)  C2      p(X  3)  C3     
4 4
., .
6 6 216 6 6 324
4 0
1 5 1
p(X  4)  C4     
4
.
6 6 1296
Hence, the required probability distribution is given by

X 0 1 2 3 4

p(X ) 625 125 25 5 1

1296 324 216 324 1296

Example 2 (a) Determine the Binomial Distribution for which the mean is 4 and standard
deviation is 3 .
Solution (a) For the Binomial Distribution,
Mean = np  4 (1)
and Standard Deviation npq  3 or npq  3 ( 2)
3 1 1
Substituting np  4 in (2), we get q  and hence, p  . Substituting p  in (1), we
4 4 4
get n  16.
Therefore, the required probability function of Binomial Distribution is
n x
f (x)  Cx . p q , where q 1  p
n x

x 16 x
1 3
, where x  0,1,2,3,......,16.
16
= Cx .   
4 4
(b) Point out the fallacy if any in the following statement; “The mean of a Binomial Distribution
is 10 and its standard deviation is 4”.
Solution. For the given Binomial Distribution, np  10 and npq  16 . Solving these two
equations we get,
16
q  1.6 >1, which is absurd. Hence the statement is not true.
10
(c)A Binomial random variable X satisfies the relation 9 p( X  4)  p( X  2) when n  6 .
Find the value of the parameter p .
Solution. For a Binomial Distribution, the probability function is
nx 6 n x
f (x)  Cx . p q  Cx . p q , where q  1  p
n x 6 x

64
p( X  4)  f (4)  C4 . p q  C4 . p q
6 4 6 4 2

62
p( X  2)  f (2)  C2 . p q  C2 . p q
6 2 6 2 4
and
By the given condition, 9 p( X  4)  p( X  2)
6 4 2 6 2 4
9. C4 . p q = C2 . p q

9p  q
2 2
or

9 p  (1  p)  1  2 p  p
2 2 2
or

8 p  2 p 1  0
2
or

8 p  4 p  2 p 1  0
2

4 p(2 p  1)  1(2 p  1)  0
or (2 p  1)(4 p  1)  0
1 1
p ,
2 4
1
Since p can not negative. Therefore, p  .
4
Example 3(a) In a Binomial Distribution consisting of 5 independent trials, the probabilities of
1 and 2 successes are 0.4096 and 0.2048 respectively. Find the parameter p of the distribution.
Solution (a) For a Binomial Distribution, the probability of x success is series of n independent
x n x x 5 x
trials is given by f (x)  Cx . p q . Here n  5 , f (x)  Cx . p q
n 5

51 52
f (1)  C1. p.q  5 pq f (2)  C2 . p .q  10 p q where q  1  p . It is given
5 4 5 2 2 3
and
that f (1)  0.4096 and f (2)  0.2048 . Then 5 pq 4  0.4096 and 10 p q  0.2048 .
2 3

Solving these equations, we get

2 3
10 p q 0.2048 2p 1
4
    4 p  q  1  p  5 p  1  p  0.2
5 pq 0.4096 q 2
(b) An unbiased coin is tossed 6 times, find, using binomial distribution, the probability of
getting at least 5 heads.
Solution. In a single throw of a coin the sample space S ={H, T}.
1 1
p (getting ahead) = and q (getting not a head) = .
2 2
r ( 6 r ) 6
( nr ) 1 1 1
p ( X  r )  Cr p q  Cr    Cr   .
n r 6 6
. 
2 2 2
 p (getting at least five heads) = p( X  5)
6 6
1 1 3 1 7
= p(X  5)  p( X  6) = C5   + C6   =   .
6 6

2 2 32 64 64
(c) An unbiased coin is tossed 8 times. Find, by using binomial distribution, the probability of
getting at least 3 heads.
Solution. In a single throw of a coin the sample space S ={H, T}.
1 1
p (getting ahead) = and q (getting not a head) = .
2 2
r (8r ) 8
( nr ) 1 1 1
p ( X  r )  Cr p q  Cr   .   Cr   .
n r 8 8

2 2 2

 p (getting at least 3 heads) = p( X  3)
= 1  [ p( X  0)  p( X  1)  p( X  2)]

 8  1 8 8  1 8 8  1 8 
= 1   C0    C1    C2   
  2  2  2  

= 1
1
1  8  28  1  37  219 .
256 256 256
Example 4 (a) Six coins are tossed simultaneously. Find the probability of getting
(i) 3 head (ii) no head (iii) at least 1 head (iv) not more than 3 heads
Solution (a) The experiment may be taken as throwing a single coin 6 times. In a single throw
of a coin the sample space S = {H, T}.
1 1
p (getting ahead) = and q (getting not a head) = .
2 2
Let X be the random variable showing the number of heads.
r ( 6 r ) 6
( nr ) 1 1 1
p ( X  r )  Cr p q  Cr      Cr  
n r 6 6

2 2 2

6
1 5
p (getting 3 heads) = p(X  3)  C3   
6
(i)
2 16
6
1 1
p (getting no head) = p(X  0)  C0   
6
(ii)
2 64
6
1 1 63
p (getting at least 1 head) = 1  p( X  0)  1 C0    1  
6
(iii)
2 64 64
(iv) p (getting not more than 3 heads) = p (no head or 1 head or 2 heads or 3 heads)
= p( X  0)  p( X  1)  p( X  2)  p( X  3)
6 6 6 6
1 1 1 1
= C0    C1    C2    C3  
6 6 6 6

2 2 2 2

6
1 1 21
=   (1  6  15  20)   42  .
2 64 32
(b)A die is thrown 5 times. If getting an odd number is a success, find the probability of getting
at least 4 success.
Solution. When a die is thrown the sample space S = {1, 2, 3, 4, 5, 6}.
3 1
p (getting an odd number) = 
6 2
1 1
p (getting a success) = and q (not getting a success) = .
2 2
Let X be the random variable showing the number of success.
r ( 5r ) 5
( nr ) 1 1 1
p ( X  r )  Cr p q  Cr      Cr  
n r 5 5

2 2 2

p ( at least 4 success) = p ( 4 success or 5 success)
5 5
1 5 1 5 1 3
= p( X  4)  p( X  5) = C4   + C5      .
5

2 2 32 32 16
(c) In 4 throws with a pair of dice, what is the probability of throwing doublets at least twice.
Solution. In a single throw of a pair of dice, the numbers of all possible outcomes are 36. The
total numbers of doublets are (1, 1), (2, 2), (3, 3), (4, 4), (5, 5), (6, 6).
 1 5
p (getting a doublet) = and q (not getting a doublet) = .
6 6
Let X be the random variable denoting the number of doublets. Then,
r ( 4 r )
( nr ) 1 5
p ( X  r )  Cr p q  Cr    
n r 4

6 6
p (at least 2 doublets) = p( X  2)  p( X  3)  p( X  4)
2 ( 4 2 ) 3 ( 43) 4 ( 4 4 )
4 1 5 1 5
4 4 1 5
= C2     + C3     + C4    
6 6 6 6 6 6
2 2 3 1 4 0
1 5 1 5 1 5
= 6     4        
6 6 6 6 6 6
25 5 1 171
=    .
216 324 1296 1296
Example 5(a) The bulbs produced in a factory are supposed to contain 5% defective bulbs.
What is the probability that a sample of 10 bulbs will contain not more than 2 defective bulbs?
5 1
Solution (a) p (getting a defective bulb) =  , p (getting a non-defective bulb)
100 20
1 19 1 19
1  . Then p and q  . Let X denote the number of defective bulbs.
20 20 6 20
r (10r )
( nr )  1   19 
p( X  r )  C r p q  Cr  
n r 10
 
 20   20 
p (getting not more than 2 defective bulbs) = p( X  0)  p( X  1)  p( X  2)
0 10 1 9 2 8
10  1   19  10  1   19  10  1   19 
 C0     + C1     + C2    
 20   20   20   20   20   20 
10 9 8 8
 1  1  19  9  19   19   149 
=   +   +      .
 20  2  20  80  20   20   100 
8
 19   149 
Let A=    . Then,
 20   100 
log A  8(log 19  log 20)  log 149  log 100
 8(1.2788  1.3010)  2.1732  2
_
 0.0044  1.9956
_
 A = antilog (1.9956)  0.99
99
Hence the required probability = .
100
 (b) If on an average, out of 10 ships, one gets drowned then what is the probability that out of
5 ships at least 4 reach the shore safely.
9
Solution. The probability of a ship to reach the shore safely  .
10
9 1
The probability that a ship gets drowned  1   .
10 10
Let X be the random variable showing the number of ships reaching the shore safely.
p (at least 4 reaching safely) = p (4 reaching safely or 5 reaching safely)
= p(4 reaching safely) + p(5 reaching safely)
= p( X  4)  p( X  5)
4 ( 54 ) 5 0
5 9 1 5 9 1
= C4     + C5    
 10   10   10   10 
4 5 4 4
1 9   9   9  1 9  7 9 
=             .
2  10   10   10   2 10  5  10 

7  (9)
4 4
7 9 
Let A    .
4 Then
5  10  5  (10)
log A  log 7  4 log 9  log 5  4 log 10
 (.8451  4  0.9542  0.6990  4
_
 0.0371  1.9629
_
 A = antilog (1.9629)  0.9181
Example 6(a) A box contains 100 transistors. 20 of which are defective, 10 are selected for
inspection. Indicate what is the probability that:
(i) all 10 are defective (ii) all 10 are good (iii) at most 03 are defective.
Solution (a) The probability of defective transistors in a sample = 0.2. The probability of non-
defective transistors in the sample = 0.8
(i) p (getting all 10 defective transistors) = p( X  10)  10C10 (0.2)10 (0.8) 0 = (0.2)10

(ii) p (getting all 10 good transistors) = 1 (0.2)10

(iii) p (getting at most 03 defective transistors) = p( X  3)
= p( X  0)  p( X  1)  p( X  2)  p( X  3)
= 10C0 (0.8)10 10C1 (0.2)(0.8) 9 10C2 (0.2) 2 (0.8) 8 10C3 (0.2) 3 (0.8) 7

= 1 0.1074  10  0.027  45  0.0067  120  0.0017  0.8814

(b) Assuming that half of the population of a town is vegetarian so that the chance of an
individual being vegetarian is half and assuming that 100 investigators can take a sample of 10
individuals to see whether they are vegetarian. How many investigators would you expect to
report that three people or less were vegetarian.
1 1
Solution. We have p , q , n  10, N  100 .
2 2
Let X be the random variable showing three or less than three people vegetarians. Then the
values of X are 0, 1, 2, 3.
The probability of r vegetarians = p( X  r )  N . nC r p r q (nr )
p (getting 03 or less vegetarians) = p( X  3)
= p( X  0)  p( X  1)  p( X  2)  p( X  3)
10 1 9 2 8 3 7
1 1 1 1 1 1 1
= 100 C 0    100 C1      10010 C 2      10010 C 3    
10 10
2 2 2 2 2 2 2
10 10 10 10
1 1 1 1
= 100     100 10   100  45   100 120 
2 2 2 2
10
1
= 100  1  10  45  120  100  1
176  17
2 1024

(c)The probability that an evening college student will graduate is 0.4. Determine the
probability that out of 05 students (i) none (ii) one (iii) at least one will be graduate.
Solution. p (graduate) =0.4 and p (not graduate) =0.6
(i) Probability that none will graduate = 5
C 0 (0.6) 5  0.08

(ii) Probability that one will graduate = C1 (0.4)(0.6) 4  0.259

5

(iii) Probability that at least one will graduate = 1 p(none will graduate) = 1  0.08  0.92
Mean and Variance of a Binomial Distribution
If a random variable X assumes the values x1, x2 , x3.........., xn with their corresponding
probabilities p1 , p2 , p3 .........., pn respectively then the mean of the random variable X is
n
defined as,    xi pi  x1 p1  x2 p2  x3 p3  ...................xn pn
i 1

For the Binomial Distribution

( n r )
where r  0,1,2,3........n
n r
p ( X  r )  p ( r )  Cr p q

The mean  is given by

n n
   r. p(r )   r.n Cr p r q ( nr )
r 0 r 0

n1 n 2
 2. C2 . p .q  ................  n. Cn . p q
n n 2 n n 0
= C1. p.q
( n 1) n 1 ( n 1) n2

0 1
= np[ C0 . p .q C1. p .q
 ( n 1) n 1 0
 ...........  Cn 1. p q ]
( n1)
= (np).(q  p)  (np)
Hence, the mean is given by   np. The variance  2 is given by
n n n
   r . p ( r )   =  r . Cr p q  (np) =  r . Cr p q
2 r ( nr ) 2 r ( nr )
 (np)
2 2 n 2 2 n 2

r 0 r 0 r 0

{r  r (r  1)}. C
( nr )
 (np)
n r 2
= r
pq
r 0

n n
=  r. C r p q  r (r  1). C
( nr ) ( nr )
  (np)
n r n r 2
r
pq
r 0 r 0

n
n(n  1)
 r (r  1). r (r  1) .
( n2 ) ( r 2 ) ( nr )
= np   (np)
2 2
Cr 2 . p p q
r 2

2 ( r  2) ( n  r ) 
n


( n  2)
   n p
2 2
= np n ( n 1). p C( r  2) p q
 r 2 
( n 2 )
= np  n(n  1) p (q  p) n p
2 2 2

= np  n(n  1) p  n p
2 2 2
[ p  q  1]

= np  np  np(1  p)  npq
2

  npq and standard deviation   npq

2
Hence, variance .
Example 1 (a) If X follows a binomial distribution with mean 3 and variance 3/2, find
(i) p( X  1) (ii) p( X  5)
Solution (a) We know that the mean  np and the variance npq .
3 3 1
 np  3 and npq   3q   q  .
2 2 2
1 1 1 1
 p  (1  q)  1   . Now np  3 and p   n   3  n  6.
2 2 2 2
So, the binomial distribution is given by
r ( 6 r ) 6
( n r ) 1 1 1
p( X  r ) Cr p q  Cr      Cr   .
n r 6 6

2 2 2

6
1 1 63
(i) p( X  1)  1  p( X  0)  1  C0    1  
6
.
2 64 64
6
1 1 63
(ii) p( X  5)  1  p( X  6)  1  C6    1  
6
.
2 64 64
(b) If X follows a binomial distribution with mean 4 and variance 2, find p( X  5) .
Solution. We know that the mean  np and the variance = npq .
1
 np  4 and npq  2 . Now np  4 and npq  2  q  .
2
1 1 1 1
 p  (1  q)  1   . Now np  4 and p   n   4  n  8.
2 2 2 2
So, the binomial distribution is given by
r ( 8r ) 8
( nr ) 1 1 1
p ( X  r )  Cr p q  Cr    Cr   .
n r 8 8
 
2 2 2
 p( X  5)  p( X  5)  p( X  6)  p( X  7)  p( X  8)
8 8 8 8
1 8 1 8 1 8 1
8
= C5   + C6   + C7   + C8  
2 2 2 2
8
1 1 93
= [ C5  C6  C7  C8 ]  = [56 + 28 + 8 +1]. 
8 8 8 8
.
2 256 256
Example 2(a) Find the binomial distribution for which the mean and variance are 12 and 3
respectively.
Solution (a) Let X be a binomial variate for which mean = 12 and the variance = 3.
1 1 3
Then np  12 and npq  3  q  and p  (1  q)  1   .
4 4 4
12 4 3 1
Also np  12  n   12   16 .Thus, n  16 , p  and q  .
p 3 4 4
Hence, the binomial distribution is given by
r (16r )
3 1
p ( X  r )  Cr     , where r  0,1,2,3,4,5...............15.
16

4 4
(b) If the sum of the mean and variance of a binomial distribution for 5 trials is 1.8, find the
distribution.
Solution. If the sum of the mean and variance of a binomial distribution for 5 trials is 1.8, find
the distribution.
We know that mean = np and the variance = npq.
It is being given that n =5 and the mean + variance = 1.8
  np  npq  1.8
 5 p  5 pq  1.8
 p  p (1  p )  0.36
 p  2 p  0.36  0
2

 100 p  200 p  36  0
2

 25 p  50 p  9  0
2

 25 p  45 p  5 p  9  0
2

 5 p (5 p  9)  (5 p  9)  0
 (5 p  9)(5 p  1)  0
1
 p   0.2 [ p can not more than 1]
5
Thus, n  5 , p  0.2 and q  (1  p)  (1  0.2)  0.8
Let X denotes the binomial variate. Then, the required distribution is
p( X  r ) Cr 0.2 0.8
( 5r )
, where r  0,1,2,3,4,5.
5 r

(c) What is the probability of guessing correctly at least six of the ten answers in a true false
objective test.
n x
Solution. We have f ( x)  Cx p q , where q  1  p.
n x

1 1
Here n  10 , p , q  , x  6,7,8,9,10 .
2 2
The required probability  f (6)  f (7)  f (8)  f (9)  f (10)
6 106 7 107 8 10 8
1 1 1 1 1 1
 C7      C8    
10 10 10
= C6    
2 2  2 2 2 2
9 109 10 1010
1 1 1 1
 C9    C10    
10 10
 
2 2 2 2

   
10 10
 1  10  1  10
C6  C7  C8  C9  C10 =   C4  C3  C2  C1  1
10 10 10 10 10 10 10
= 
2 2
=
1
210  120  45  10  1  386  193 .
1024 1024 512
Example 3 (a) The sum and the product of the mean and variance of a binomial distribution are
24 and 128 respectively, find the distribution.
Solution (a) We have , np  npq  24 and np  npq  128.
 np(1  q)  24 and n p  q  128
2 2

576
n p 
2 2 2 2
and n p  q  128
(1  q)
2

576 128
   2(1  q  2q)  9q
2

(1  q)
2
q
  2q  5q  2  0  (2q  1)(q  2))  0
2

1
q [q  0]
2
1 1
 p  (q  1)  1   .
2 2
1 1
Now, np(1  q)  24  n  1    24  n  32.
2 2
32
1
Hence, the required probability distribution is given by p( X  r ) Cr   .
32

2
(b) In a binomial distribution prove that mean > variance.
Solution. Let X be the binomial variate with parameters n and p. Then mean = np and the
variance = npq.
mean – variance  np  npq  np(1  q)  np  0
2


 [(mean) –(variance)] > 0

 mean > variance.
Example 4 (a) A die is tossed twice. Getting an even number is considered a success, what is
the variance of the binomial distribution.
Solution (a) Here, n = 3. Let p be the probability of getting an even number in a single throw
3 1 1 1 1 1 3
then p   .  q  (1  p)  1   . Thus, variance = npq  3    .
6 2 2 2 2 2 4
(b) A die is tossed 180 times. Find the expected number of times the face with the number 5
will appear. Also, find the standard deviation and variance.
1
Solution. In a single die S = {1, 2, 3, 4, 5, 6}, p (prob. of getting the number 5) =
6
1 5 1 5 1
 q  (1  p)  1   . Thus, n  180 , p , q  . ,   np  180   30.
6 6 6 6 6
1 5
Variance   npq  180    25, Standard deviation   25  5.
2

6 6
Example 5. The screw produced by a certain machine were checked by examining samples of
12. The following table shows the distribution of 128 samples according to the number of
defective items they contained

No. of defectives 0 1 2 3 4 5 6 7 Total

in a sample of 12

No. of samples 7 6 19 35 30 23 7 1 128

Fit a binomial distribution and find the expected frequencies if the chance of screw being
defective is 1/2. Find the mean and variance of fitted distribution.
Solution Computation of frequencies
 No. of Probabilities Expected Observed
defectives frequency frequency
0 7
1 1 1
0 p( X  0) 7 C 0      . 1 7
2 2 128
1 6
1 1 7
1 p( X  1) 7 C1      . 7 6
2 2 128
2 5
2 1 1 21
p( X  2) 7 C 2      .
2 2 128 21 19
3 3
1 1 35
4
p( X  3) 7 C 3      . 35 35
   
2 2 128
4 4 3
1 1 35 35 30
p( X  4) 7 C 4     
 2   2  128
5 5
1 1 21
2 21 23
p( X  5) 7 C 5      .
   
2 2 128
6 1 7 7
1 1 7
6 p( X  6) C 6     
7
.
   
2 2 128 1 1
7 0
7 1 1 1
p ( X  7)  7 C 7      .
2 2 128

r 7r
1 1
Probabilities = p( X  r ) C r    
7
, Expected frequencies 128  p( X  r )
2 2
1
Arithmetic Mean = np  7   3.5 , Variance = npq  7  1  1  1.75
2 2 2