Chapter 5 Section 1

Examples
Example 5.1:
For the given case, the component will either survive or not with the condition that if one
survives it does not change the fact that the second will survive or not. Hence, this is a baernoulli
trial. We have for the given trial:

n = 4 ; x = 2 ; p = 3/4 ; q = 1 - p = 1- 3/4 = 1/4

Now, using the formula for a binomial distribution, we have:

b ( x :n , p ) = b(2: 4, 3/4) = ❑4 C2 ¿ (3/4)❑2 ¿ (1/4)❑4 − 2 = 6 ¿ 9/16 ¿ 1/16 = 27/128

Example 5.2:
For the given case, the patient will either survive or not with the condition that if one survives it
does not change the fact that the second will survive or not. Hence, this is a bernoulli trial. Now,
we have for the given cases:

n = 15; p = 0.4 ; q = 1 - p = 1 - 0.4 = 0.6

(a) We have for at least 10 to survive:

P ( X >10 ) = 1 - P ( X <10 ) = 1 - Σ 9x=0 b ( x :15 , 0.4 ) ---(i)

Now, for:
9 15 15 15
Σ x=0 b ( x :15.0 .4 ) = ❑ C 0 ¿ (0.4)❑0 ¿ (0.6)❑15− 0 + ❑ C 1 ¿ (0.4)❑1 ¿ (0.6)❑15− 1 + ❑ C 2 ¿ (0.4)
15 15 15
❑ ¿ (0.6)❑ + ❑ C 3 ¿ (0.4)❑3 ¿ (0.6)❑15− 3 + ❑ C 4 ¿ (0.4)❑4 ¿ (0.6)❑15− 4 + ❑ C 5 ¿ (0.4)❑5
2 15− 2

¿ (0.6)❑15− 5 + ❑15 C 6 ¿ (0.4)❑6 ¿ (0.6)❑15− 6 + ❑15 C 7 ¿ (0.4)❑7 ¿ (0.6)❑15− 7 + ❑15 C 8 ¿ (0.4)❑8 ¿

15
(0.6)❑15− 8 + ❑ C 9 ¿ (0.4)❑9 ¿ (0.6)❑15− 9 = 0.0004701 + 0.004701 + 0.0219 + 0.06338 +
0.12677 + 0.18594 + 0.2066 + 0.1771 + 0.1180 + 0.0612 = 0.9661

(i) => P ( X >10 ) = 1 - 0.9661 = 0.0339

(b) We have from 3 to 8 survive:

P ( 3< X < 8 ) = P ( X <8 ) - P ( X <3 ) = Σ 7x=0 b ( x :15 , 0.4 ) - Σ 2x=0 b ( x :15 , 0.4 ) = 0.9050 - 0.0271 =
0.8779

(Note: Σ values are calculated using the method mentioned in part (a) )

(c) We have for exactly 5 to survive:

P ( X=5 ) = b ( 5 :15 , 0.4 ) = ❑15 C 5 ¿ (0.4)❑5 (0.6)❑10 = 0.1859

Example 5.3:
The device to be selected is either defective or non-defective i.e. it is a trial of either success or
failure, such that if one device is defected it does not have an impact on whether the other is
defective or not. Thus, this is a bernoulli trial, for which we have:

p = 3% = 0.03 ; q = 1 - p = 1 - 0.03 = 0.97

(a) We have, for the given case:

n = 20 ; x >= 1

P ( X >¿ 1 ) = 1 - P(X = 0) = 1 - b ( 0 :20 , 0.03 ) = 1 - ❑20 C 0 ¿ (0.03)❑0 ¿ (0.97)❑20 = 1 - 1 ¿ 1 ¿ 0.5438 =

1 - 0.5438 = 0.4562

(b) For this case, we suppose X is the random variable representing the number of defective
devices in a shipment of 20 devices and Y be the random variable representing the number of
shipments that will contain a defective device, then:

Using part(a), we have for atleast one defective device in a shipment:

P ( X >¿ 1 ) = 0.4562
Now, we have for the number of shipments with defective devices:

n = 10; y = 3; p = 0.4562; q = 1 - p = 1 - 0.4562 = 0.5438

P ( Y =3 ) = b ( y :n , p ) = b ( 3 :10 , 0.4562 ) = ❑10 C 3 ¿ (0.4562)❑3 ¿ (0.5438)❑7 = 120 ¿ 0.0949 ¿

0.0141 = 0.1608

Example 5.4:
The wells are either filled with impure water or pure water, hence, the trial is either a success or
a failure with the case that a certain containing impure water doesn't have an impact on the
other wells as to whether they will be impure or not. No, for the given case, we have:

n = 10; p = 30% = 0.3 ; q = 1 - p = 1 - 0.3 = 0.7

(a) For the given case, we have:

P ( X=3 ) = b ( x :n , p ) = ❑10 C 3 ¿ (0.3)❑3 ¿ (0.7)❑7 = 120 ¿ 0.027 ¿ 0.082 = 0.2656

(b) For the given case, we have:

P ( X >3 ) = 1 - P( X < ¿3 ) = 1 - Σ 3x=0 b ( x : n , p ) = 1 - (b ( 0 :10 , 0.3 ) + b ( 1 :10 , 0.3 ) + b ( 2 :10 , 0.3 ) +

b ( 3 :10 , 0.3 ) ) = 1 - (❑10 C 0 ¿ (0.3)❑0 ¿ (0.7)❑10− 0 + ❑10 C 1 ¿ (0.3)❑1 ¿ (0.7)❑10− 1 + ❑10 C 2 ¿ (0.3)❑2
¿ (0.7)❑10− 2 + ❑10 C 3 ¿ (0.3)❑3 ¿ (0.7)❑10− 3) = 1 - (0.0282 + 0.1211 + 0.2335 + 0.2668) = 1 -
0.6496 = 0.3504

Example 5.5:
For the example in 5.2, we have:
n = 15; p = 0.4; q = 0.6

Mean = μ = np = (15)(0.4) = 6 ; Variance = σ 2 = npq = (15)(0.4)(0.6) = 3.6

Now, to apply Chebyshev's theorem, we need std(Standard Deviation) i.e.

σ = √ σ 2 = √ 3.6 = 1.897

Thus, we have by Chebyshev's theorem, the interval: μ +- 2σ = 6 - 2(1.897) to 6 + 2(1.897) = 2.206

to 9.794

Example 5.6:
Considering the case in Example 5.4, we have:

n = 10; p = 0.3; q = 0.7

P ( X ≥6 ) = 1 - P ( X <5 ) = 1 - Σ 5x=0 b ( x :10 , 0.3 ) = 1 - (b ( 0 :10 , 0.3 ) + b ( 1 :10 , 0.3 ) + b ( 2 :10 , 0.3 ) +
b ( 3 :10 , 0.3 ) + b ( 4 :10 , 0.3 ) + b ( 5 :10 , 0.3 )) = 1 - (❑10 C 0 ¿ (0.3)❑0 ¿ (0.7)❑10− 0 + ❑10 C 1 ¿ (0.3)❑1 ¿
10 10 10
(0.7)❑10− 1 + ❑ C 2 ¿ (0.3)❑2 ¿ (0.7)❑10− 2 + ❑ C 3 ¿ (0.3)❑3 ¿ (0.7)❑10− 3 + ❑ C 4 ¿ (0.3)❑4 ¿
10
(0.7)❑10− 4 + ❑ C 5 ¿ (0.3)❑5 ¿ (0.7)❑10− 5) = 1 - (0.0282 + 0.1211 + 0.2335 + 0.2668 + 0.2001 +
0.1029) = 1 - 0.9526 = 0.0474

Conclusion: As a result, it is very unlikely (4.7% chance) that 6 or more wells would be found
impure if only 30% of all are impure. This casts considerable doubt on the conjecture and
suggests that the impurity problem is much more severe.

Example 5.7:
Assume that R1, R2 and R3 be the events that the airplanes access the runways 1,2 and 3
respectively, then we have:

p1 = P(R1) = 2/9 ; p2 = P(R2) = 1/6 ; p3 = P(R3) = 11/18 ; x 1 = 2 ; x 2 = 1 ; x 3 = 3 ; n = 6

Now, using formula for multinomial distribution:

f ( x 1 , x 2 , x3 ; p 1, p 2 , p 3 , n ) = f ( 2 , 1 ,3 ; 2/9 , 1/6 , 11/18 , 6 ) = (6!/(2! ¿ 1! ¿ 3!)) ¿ (2/9)❑2 ¿ (1/6)❑1 ¿

(11/18)❑3 = 60 ¿ 4/81 ¿ 1/6 ¿ 1331/5832 = 0.1127

Exercises:
Exercise 5.1:
For the given function, we have: p X ( x ) = 1/k

Mean = μ = E [ X ) = Σ x x p X ( x ) = Σ i=1 x i /k
k

2 k 2
Variance = σ 2 = Σ x ( x − μ ) p X ( x ) = Σ i=1 ( x i − μ ) /k

Exercise 5.2:
Let D be the event that the person finds a difference and N be the event that he does not. Let X
be the random variable representing the number of people who heard a difference between the
speakers. Since, the trial has only two possible outcomes i.e. either the person will hear a
difference or not, such that the claim of one person does not affect the claim of the other, thus,
this is a bernoulli trial, for which we have:

n = 12; x = 3; p = 0.5; q = 1 - p = 1 - 0.5 = 0.5

(We take probability as 0.5 because both the events are equally likely and the people are
guessing randomly)

Now, using formula for binomial distribution:

P ( X=3 ) = b ( x :n , p ) = b ( 3 :12 , 0.5 ) = ❑12 C 3 ¿ (0.5)❑3 ¿ (0.5)❑12− 3 = 0.0537

Exercise 5.3:
For the given case, let X be the random variable representing the tag number that has been
selected. Now, since at most one tag can be selected at a time from a total of 10, the probability
for selecting a certain tag at random would be given by the probability distribution formula:

p X ( x ) = 1/10 ; x = 1,2,3,....10 and p X ( x ) = 0 ; otherwise

Now, for probability that a number less than 4 is drawn, we have:

n = 10; p = 1/10 = 0.1; q = 1 - p = 1 - 0.1 = 0.9

P ( X < 4 ) = Σ 3x=1 b ( x :n , p ) = b ( 1 :10 , 0.1 ) + b ( 2 :10 , 0.1 ) + b ( 3 :10 , 0.1 ) = ❑10 C 1 ¿ (0.1)❑1 ¿ (0.9)
10 10
❑
10− 1
+ ❑ C 2 ¿ (0.1)❑2 ¿ (0.9)❑10− 2 + ❑ C 3 ¿ (0.1)❑3 ¿ (0.9)❑10− 3 = 0.3874 + 0.1937 + 0.0574 =
0.6385

Exercise 5.4:
Let X be the random variable representing the number of cases caused due to need for money to
buy drugs, then we have:

n = 5; p = 75% = 0.75; q = 1 - p = 1 - 0.75 = 0.25

This is a bernoulli trial, as the reason for theft may either be caused by the need for money to
buy drugs or not, such that the reason for first theft will not affect the reason for the second

(a) For the given case, we have:

P ( X=2 ) = b ( 2 :5 , 0.75 ) = ❑5 C 2 ¿ (0.75)❑2 ¿ (0.25)❑5 −2 = 0.0878

(b) For the given case, we have: (At most 3 means not more than 3)

P ( X ≤3 ) = Σ 3x=0 b ( x : n , p ) = b ( 0 :5 , 0.75 ) + b ( 1 :5 , 0.75 ) + b ( 2 :5 , 0.75 ) + b ( 3 :5 , 0.75 ) = ❑5 C 0 ¿

5 5 5
(0.75)❑0 ¿ (0.25)❑5 −0 + ❑ C 1 ¿ (0.75)❑1 ¿ (0.25)❑5 −1 + ❑ C 2 ¿ (0.75)❑2 ¿ (0.25)❑5 −2 + ❑ C 3 ¿
(0.75)❑3 ¿ (0.25)❑5 −3 = 0.00098 + 0.01464 + 0.08789 + 0.26367 = 0.36718
Exercise 5.5:
Let X be the random variable representing the number of pipework failures caused by operator
error, then we have:

p = 30% = 0.3 ; q = 1 - p = 1 - 0.3 = 0.7

(a) For the given case, we have:

n = 20; x ≥ 10

P ( X ≥10 ) = 1 - P ( X <9 ) = 1 - Σ 9x=0 b ( x : n , p ) = 1 - (b ( 0 :20 , 0.3 ) + b ( 1 :20 , 0.3 ) + b ( 2 :20 , 0.3 ) +

b ( 3 :20 , 0.3 ) + b ( 4 :20 , 0.3 ) + b ( 5 :20 , 0.3 ) + b ( 6 :20 , 0.3 ) + b ( 7 :20 , 0.3 ) + b ( 8 :20 , 0.3 ) +
b ( 9 :20 , 0.3 ) ) = 1 - (0.00079 + 0.00684 + 0.02784 + 0.07160 + 0.13042 + 0.17886 + 0.19164 +
0.16426 + 0.11439 + 0.06537) = 1 - 0.95201 = 0.04799

(b) For the given case, we have:

P ( X ≤ 4 ) = Σ 4x=0 b ( x : n , p ) = b ( 0 :20 , 0.3 ) + b ( 1 :20 , 0.3 ) + b ( 2 :20 , 0.3 ) + b ( 3 :20 , 0.3 ) +

b ( 4 :20 , 0.3 ) = 0.00079 + 0.00684 + 0.02784 + 0.07160 + 0.13042 = 0.28749
(c) For the given case, we have:

P ( X=5 ) = b ( 5 :20 , 0.3 ) = ❑20 C 5 ¿ (0.3)❑5 ¿ (0.7)❑20− 5 = 0.17886 (The probability is close to that
given i.e. 0.3, hence, the figure of 30% applies to the plant)

Exercise 5.6:
Let X be the random variable representing the companies that give a vacation of 4 weeks to
employees after 15 years, we have:

n = 6; p = 0.5; q = 1 - p = 1 - 0.5 = 0.5

(We take probability as 0.5 as the chance of getting vacations or not is equally likely)

(a) For the given case, we have:

P ( 2≤ X ≤ 5 ) = P ( X ≤5 ) - P ( X ≤1 ) = (1 - P ( X=6 )) - P ( X ≤1 ) = (1 - b ( 6 :6 ,0.5 )) - ( Σ 1x=0 b ( x : n , p ) ) = (1

- 0.0156) - (b ( 0 :6 , 0.5 ) + b ( 1 :6 , 0.5 ) ) = 0.9844 - (0.0156 + 0.09375) = 0.9844 - 0.1093 = 0.8751

(b) For the given case, we have:

P ( X <3 ) = Σ 2x=0 b ( x : n , p ) = b ( 0 :6 , 0.5 ) + b ( 1 :6 , 0.5 ) + b ( 2 :6 , 0.5 ) = 0.0156 + 0.09375 + 0.2343 =

0.3436

Exercise 5.7:
Let X be the random variable representing the number of patients with lung cancer that are
chain smokers, then we have:

p = 70% = 0.7; q = 1 - p = 1 - 0.7 = 0.3

(a) For the given case, we have:

n = 10; x < n/2 = 5

P ( X <5 ) = Σ 4x=0 b ( x : n , p ) = b ( 0 :10 , 0.7 ) + b ( 1 :10 , 0.7 ) + b ( 2 :10 , 0.7 ) + b ( 3 :10 , 0.7 ) +
b ( 4 :10 , 0.7 ) = 0.000006 + 0.000138 + 0.001446 + 0.009002 + 0.036757 = 0.04735
(b) For the given case, we have:

n = 20; x < n/2 = 10

P ( X <10 ) = Σ 9x=0 b ( x : n , p ) = b ( 0 :20 , 0.7 ) + b ( 1 :20 , 0.7 ) + b ( 2 :20 , 0.7 ) + b ( 3 :20 , 0.7 ) +
b ( 4 :20 , 0.7 ) + b ( 5 :20 , 0.7 ) + b ( 6 :20 , 0.7 ) + b ( 7 :20 , 0.7 ) + b ( 8 :20 , 0.7 ) + b ( 9 :20 , 0.7 ) = 0.0171
(Note: Values will be computed in the same procedure)

Exercise 5.8:
Let X be the random variable representing the users that took Valium for psychological
problems, then we have:

n = 8; p = 60% = 0.6; q = 1 - p = 1 - 0.6 = 0.4

(a) For the given case, we have:

P ( X=3 ) = b ( 3 :8 , 0.6 ) = ❑8 C 3 ¿ (0.6)❑3 ¿ (0.4)❑8 −3 = 0.1238

(b) For the given case, we have if there are atleast 5 people taking Valium for non-psychological
problems then at most 3 people will be taking it for psycological problems i.e.

P ( X ≤3 ) = Σ 3x=0 b ( x : n , p ) = b ( 0 :8 , 0.6 ) + b ( 1 :8 , 0.6 ) + b ( 2 :8 , 0.6 ) + b ( 3 :8 , 0.6 ) = 0.00065 +

0.00786 + 0.04128 + 0.12386 = 0.17365

Exercise 5.9:
Let X be the random variable representing the trucks that fail without a blowout, then we have:

n = 15; p = 25% = 0.25; q = 1 - p = 1 - 0.25 = 0.75

(a) For the given case, we have:

P ( 3 ≤ X ≤ 6 ) = Σ 6x=3 b ( x :n , p ) = b ( 3 :15 , 0.25 ) + b ( 4 :15 , 0.25 ) + b ( 5 :15 , 0.25 ) + b ( 6 :15 , 0.25 ) =

0.2252 + 0.2252 + 0.1651 + 0.0917 = 0.7072

(b) For the given case, we have:

P ( X < 4 ) = Σ 3x=0 b ( x : n , p ) = b ( 0 :15 , 0.25 ) + b ( 1 :15 , 0.25 ) + b ( 2 :15 , 0.25 ) + b ( 3 :15 , 0.25 ) = 0.0134
+ 0.0668 + 0.1559 + 0.2252 = 0.4613

(c) For the given case, we have:

P ( X >5 ) = 1 - P ( X ≤5 ) = 1 - ( Σ 5x=0 b ( x : n , p ) ) = 1 - (b ( 0 :15 , 0.25 ) + b ( 1 :15 , 0.25 ) + b ( 2 :15 , 0.25 ) +
b ( 3 :15 , 0.25 ) + b ( 4 :15 , 0.25 ) b ( 5 :15 , 0.25 )) = 1 - (0.0134 + 0.0668 + 0.1559 + 0.2252 + 0.2252 +
0.1651) = 1 - 0.8516 = 0.1484

Exercise 5.10:
Let X be the random variable representing the seniors who disapprove of daily pot smoking,
then we have:

n = 12; p = 70% = 0.7; q = 1 - p = 1 - 0.7 = 0.3

(a) For the given case, we have:

P ( 7 ≤ X ≤ 9 ) = Σ 9x=7 b ( x : n , p ) = b ( 7 :12 , 0.7 ) + b ( 8 :12 , 0.7 ) + b ( 9 :12 , 0.7 ) = 0.1585 + 0.2311 +

0.2397 = 0.6293

(b) For the given case, we have:

P ( X ≤5 ) = Σ 5x=0 b ( x : n , p ) = b ( 0 :12 , 0.7 ) + b ( 1 :12 ,0.7 ) + b ( 2 :12 ,0.7 ) + b ( 3 :12 , 0.7 ) +

b ( 4 :12 ,0.7 ) + b ( 5 :12 , 0.7 ) = 0.0000005 + 0.0000149 + 0.0001909 + 0.0014852 + 0.0077977 +
0.0291114 = 0.0386

(c) For the given case, we have:

P ( X ≥ 8 ) = 1 - P ( X ≤7 ) = 1 - ( Σ 7x=0 b ( x : n , p ) ) = 1 - (b ( 0 :12 , 0.7 ) + b ( 1 :12 ,0.7 ) + b ( 2 :12 ,0.7 ) +

b ( 3 :12 , 0.7 ) + b ( 4 :12 ,0.7 ) + b ( 5 :12 , 0.7 ) + b ( 6 :12 , 0.7 ) + b ( 7 :12 , 0.7 ) ) = 1 - (0.0000005 +
0.0000149 + 0.0001909 + 0.0014852 + 0.0077977 + 0.0291114 + 0.0792478 + 0.1584958) = 1 -
0.2763 = 0.7237

Exercise 5.11:
Let X be the random variable representing the number of patients that survive then we have:

n = 7; x = 5; p = 0.9; q = 1 - p = 1 - 0.9 = 0.1

Now,

P ( X=5 ) = b ( 5 :7 , 0.9 ) = ❑7 C 5 ¿ (0.9)❑5 ¿ (0.1)❑7 −5 = 21 ¿ 0.5905 ¿ 0.01 = 0.124

Exercise 5.12:
Let X be the random variable representing the number of vehicles out of state, then we have:
(note that probability of X will be 25% as the given probability is for vehicles in the state)

n = 9; p = 25% = 0.25; q = 1 - p = 1 - 0.25 = 0.75

For the given case i.e. less than 4 vehicles, we have:

P ( X < 4 ) = Σ 3x=0 b ( x : n , p ) = b ( 0 :9 , 0.25 ) + b ( 1 :9 , 0.25 ) + b ( 2 :9 , 0.25 ) + b ( 3 :9 , 0.25 ) = 0.075 +

0.225 + 0.300 + 0.234 = 0.834
Exercise 5.13:
Let X be the random variable representing the people that hold the given opinion then we have:

n = 5 ; x = 3; p = 70% = 0.7; q = 1 - p = 1 0.7 = 0.3

Now, we have:

P ( X=3 ) = b ( 3 :5 , 0.7 ) = ❑5 C 3 ¿ (0.7)❑3 ¿ (0.3)❑5 −3 = 10 ¿ 0.343 ¿ 0.09 = 0.3087

Exercise 5.14:
Let X be the random variable representing the wins for the Chicago Bulls in the game, then we
have: (Best of 7 series is a series in which 7 games are played 3-3 and then final game is decided
using the fourth game)

n = 7; p = 90% = 0.9; q = 1 - p = 1 - 0.9 = 0.1

(a) For the Bulls to sweep (4-0) we have:

P ( X=4 ) = b ( 4 :7 , 0.9 ) = ❑7 C 4 ¿ (0.9)❑4 ¿ (0.1)❑7 −4 = 35 ¿ 0.6561 ¿ 0.001 = 0.0229

(b) For the Bulls to win the best of 7 series (they can either sweep (4-0), (5-0), (6-0), (7-0)),
hence we have:

P ( 4 ≤ X ≤ 7 ) = Σ 7x=4 b ( x :n , p ) = b ( 4 :7 , 0.9 ) + b ( 5 :7 , 0.9 ) + b ( 6 :7 , 0.9 ) + b ( 7 :7 , 0.9 ) = 0.0229 +

0.1240 + 0.3720 + 0.4783 = 0.9972

(c) For the given case, we assume the fact that the Bulls always win by a probability of 0.9 in the
games.

Exercise 5.15:
Let X be the random variable representing the number of mice that contract the disease, then we
have: (probability for the variable will be 40% because we are given for mice to be protected
whereas we are calculating for them to contract the disease)

n = 5; p = 40% = 0.4; q = 60% = 0.6

(a) For the given case, we have:

P ( X=0 ) = b ( 0 :5 , 0.4 ) = 0.6❑5 = 0.0777

(b) For the given case, we have:

P ( X <2 ) = Σ 1x=0 b ( x : n , p ) = b ( 0 :5 , 0.4 ) + b ( 1 :5 , 0.4 ) = 0.0777 + 0.2592 = 0.3369

(c) For the given case, we have:

P ( X >3 ) = P ( X=4 ) + P ( X=5 ) = b ( 4 :5 , 0.4 ) + b ( 5 :5 , 0.4 ) = 0.0768 + 0.0102 = 0.087

Exercise 5.16:
Let X be the random variable representing the number of engines for which the aeroplane lands
a safe flight, then we have: (This will be 0.6 since we are given the probability of failing)

p = 0.6; q = 0.4

For the 2-Engine Plane: For the 2-engine plane, atleast 1 of its engine should be running i.e. we
have: n = 2

P ( X ≥1 ) = 1 - P ( X=0 ) = 1 - b ( 0 :2 , 0.6 ) = 1 - ❑2 C 0 ¿ (0.6)❑0 ¿ (0.4)❑2 = 1 - 0.16 = 0.84

For the 4-Engine Plane: For the 4-engine plane, atleast 2 of its engines should be running i.e. n
=4

P ( X ≥2 ) = 1 - P ( X ≤1 ) = 1 - ( P ( X=0 ) + P ( X=1 )) = 1 - (b ( 0 : 4 , 0.6 ) + b ( 1 :4 ,0.6 )) = 1 - (0.0256 +

0.1536) = 1 - 0.1792 = 0.8208

Hence, the 2-engine plane has more probability of survival

Exercise 5.17:
We have from the case in Example 5.13:

n = 5; p = 0.7; q = 0.3

Mean = μ = np = (5)(0.7) = 3.5; Variance = σ 2 = npq = (5)(0.7)(0.3) = 1.05

Exercise 5.18:
We have from the case in Example 5.9:

n = 15; p = 0.25; q = 0.75

(a) For the given case , we have:

Expected Value = Mean = μ = np = (15)(0.25) = 3.75

(b) For the given case, we have:

Variance = σ 2 = npq = (15)(0.25)(0.75) = 2.8125

Exercise 5.19:
For the given conditon, we have:
X 1: the number of times student encounters a green light

X 2 : the number of times student encounters a yellow light

X 3 : the number of times student encounters a red light

Now, assuming that the probabilities for the given random variables are p1, p2 and p3
respectively, we have:
p1 = 35/100 = 0.35; p2 = 5/100 = 0.05; p3 = 60/100 = 0.6
We have for the multi-nomial distribution for total time n:

f =( n! / ( x 1 !∗x 2 !∗x 3 ! ) )∗( 0.35 ) x ∗( 0.05 ) x ∗( 0.6 )x

1 2 3

Excercise 5.20:
Let C be the random variable representing the cocaine users, M be the random variable
representing the marijuana users and X be the random variable representing users for other
drugs, then we have:
p M = 54.4% = 54.4/100 = 0.544; pC = 22.5% = 22.5/100 = 0.225; p X = 1 - pC - p M = 1 - 0.769 =
0.231

(a) For the given case, we have:

n = 10; c = 2; m = 5; x = 3

P ( C=2 , M =5 , X =3 ) = f ( c , m , x : pC , p M , p X , n ) = f ( 2 , 5 , 3: 0.544 , 0.225 , 0.231, 10 ) = 10!/(2! ¿ 5!

¿ 3!) ¿ (0.225)❑2 ¿ (0.544)❑5 ¿ (0.231)❑3 = 2520 ¿ 0.0506 ¿ 0.0476 ¿ 0.0123 = 0.0746
(b) For the given case, we have:

n = 10; c = 0; m = 10; x = 0;

P ( C=0 , M =10 , X=0 ) = f ( 0 ,10 , 0 :0.225 , 0.544 , 0.231 , 10 ) = 10!/10! ¿ (0.225)❑0 ¿ (0.544)❑10 ¿
(0.231)❑0 = 0.0023

(c) For the given case, we can say:

n = 10; c = 0; y = m + x = 10 => pY = 0.544 + 0.231 = 0.775

P ( C=0 ,Y =10 ) = f ( 0 ,10 :0.225 , 0.775 , 10 ) = 10!/(0! ¿ 10!) ¿ (0.225)❑0 ¿ (0.775)❑10 = 0.0782

Exercise 5.21:
Let:

B: Random variable representing the number of Bull's eye hit

T: Random variable representing the number of Triples hit

D: Random varaible representing the number of Doubles hit

S: Random variable representing the number of Single hit

M: Random variable representing the number of Complete Miss

For given situation, we have:

pB = 0.01; pT = 0.05; p D = 0.10; p M = 0.02; pS = 1 - ( pB + pT + p D + p M ) = 1 - 0.18 = 0.82

Now, we have:
P ( B=0 , T =0 , D=2 , S=4 , M =1 ) = f ( b ,t , d , s , m:0.01 , 0.05 , 0.10 , 0.82 ,0.02 , 7 ) = 7!/(2! ¿ 4! ¿ 1!)
¿ (0.01)❑0 ¿ (0.05)❑0 ¿ (0.10)❑2 ¿ (0.82)❑4 ¿ (0.02)❑1 = 0.0095

Exercise 5.22:
Let:

B: Random variable representing the number of black guinea pigs

W: B: Random variable representing the number of white guinea pigs

R: B: Random variable representing the number of red guinea pigs

For given situation, we have:

R:B:W = 8:4:4 = 2:1:1 => p R = 1/2 = 0.5 ; PB = 1/4 = 0.25 ; PW = 1/4 = 0.25

Now, we have:

P ( R=5 , B=2 , W =1 ) = f ( r , b , w : 0.5 ,0.25 ,0.25 , 8 ) = 8!/(5! ¿ 2! ¿ 1!) ¿ (0.5)❑5 ¿ (0.25)❑2 ¿ (0.25)
❑ = 0.082
1

Exercise 5.23:
Let:

A: Random variable representing the arrival of delegate by air

B: Random variable representing the arrival of delegate by bus

M: Random variable representing the arrival of delegate by automobile

T: Random variable representing the arrival of delegate by train

For given condition, we have:

p A = 0.4; pB = 0.2; p M = 0.3; pT = 0.1

We have:

P ( A=3 , B=3 ; M =1 ; T =2 ) = f ( a , b , m, t :0.4 ,0.2 , 0.3 , 0.1 , 9 ) = 9!/(3! ¿ 3! ¿ 1! ¿ 2!) ¿ (0.4)❑3 ¿

(0.2)❑3 ¿ (0.3)❑1 ¿ (0.1)❑2 = 0.00774

Exercise 5.24:
Let X be the number of workers wearing safety helmets while eating lunch, then we have:

x = 4; n = 6; p = 40% = 0.4; q = 1 - p = 1 - 0.4 = 0.6

Now, we have:

P ( X=4 ) = b ( 4 :6 , 0.4 ) = ❑6 C 4 ¿ (0.4)❑4 ¿ (0.6)❑6 −4 = 0.1382

Exercise 5.25:
Let X be the number of chips that fail, then we have:

x = 3; n = 20; p = 0.1; q = 1 - p = 1 - 0.1 = 0.9

Now, we have:

P ( X=3 ) = b ( 3 :20 , 0.1 ) = ❑20 C 3 ¿ (0.1)❑3 ¿ (0.9)❑20− 3 = 0.1901

Exercise 5.26:
(a) and (b) parts have been combined as the procedure is almost the same both ways (Mostly
you won't have a table like one given in Appendix A.1 so its better to perfomr using the general
method of binomial distribution)

Let X be the random variable representing the number of automobile accidents due to speed
violation, then we have:

x = 6; n = 8; p = 6/10 = 0.6; q = 1 - p = 1 - 0.6 = 0.4

Now, we have:

P ( X=6 ) = b ( 6 :8 , 0.6 ) = ❑8 C 6 ¿ (0.6)❑6 ¿ (0.4)❑8 −6 = 0.2090

Exercise 5.27:
Let X be the random variable representing the number of flourescent lights having a life of
atleast 800 hours, then we have:

n = 20; p = 0.9; q = 1 - p = 1 - 0.9 = 0.1

(a) For the given case, we have:

P ( X=18 ) = b ( 18 :20 , 0.9 ) = ❑20 C 18 ¿ (0.9)❑18 ¿ (0.1)20 −18 = 0.2852

(b) For the given case, we have:

P ( X ≥15 ) = Σ 20x=15 b ( x :n , p ) = b ( 15 :20 , 0.9 ) + b ( 16 :20 , 0.9 ) + b ( 17 :20 , 0.9 ) + b ( 18 :20 , 0.9 ) +
b ( 19 :20 , 0.9 ) + b ( 20 :20 , 0.9 ) = 0.0319 + 0.0898 + 0.1901 + 0.2852 + 0.2701 + 0.1216 = 0.9887
(c) For the given case, we have: (since at least 2 will not have a useful life at least 800 hours,
thus, atmost 18 will have useful life)

P ( X ≤18 ) = 1 - P ( X ≥19 ) = 1 - ( P ( X=19 ) + P ( X=20 )) = 1 - (b ( 19 :20 , 0.9 ) + b ( 20 :20 , 0.9 ) ) = 1 -

(0.2701 + 0.1216) = 1 - 0.3917 = 0.6083

Exercise 5.28:
Suppose that the number of toasters to be repaired after 1 year is represented by the random
variable X, then for given condition, we have:

n = 20; p = 0.2; q = 1 - p = 1 - 0.2 = 0.8

(a) For given case, we have:

P ( X ≥ x ) < 0.5 => 1 - P ( X < x ) < 0.5 => 1 - P ( X ≤ x −1 ) < 0.5

Now, we applying fomrula for binomial distribution:

=> 1 - b ( x −1: n , p ) < 0.5

For X = 1: 1 - b ( 0 :20 , 0.2 ) = 1 - 0.0115 = 0.9884 ≮ 0.5

For X = 2: 1 - (b ( 0 :20 , 0.2 ) + b ( 1 :20 , 0.2 )) = 1 - (0.0115 + 0.0576) = 0.9309 ≮ 0.5

For X = 3: 1 - (b ( 0 :20 , 0.2 ) + b ( 1 :20 , 0.2 ) + b ( 2 :20 , 0.2 )) = 1 - (0.0115 + 0.0576 + 0.1369) = 0.794
≮ 0.5
For X = 4: 1 - (b ( 0 :20 , 0.2 ) + b ( 1 :20 , 0.2 ) + b ( 2 :20 , 0.2 ) + b ( 3 :20 , 0.2 )) = 1 - (0.0115 + 0.0576 +
0.1369 + 0.2053) = 0.5887 ≮ 0.5

For X = 5: 1 - (b ( 0 :20 , 0.2 ) + b ( 1 :20 , 0.2 ) + b ( 2 :20 , 0.2 ) + b ( 3 :20 , 0.2 ) + b ( 4 :20 , 0.2 )) = 1 - (0.0115
+ 0.0576 + 0.1369 + 0.2053 + 0.1745) = 0.4142 < 5

Hence, the value of x will be 5

Chapter 5 Section 2:
Examples:
Example 5.8:
To check whether the plan suggested is acceptable or not, we apply hetrogeometric function for
2 defective parts i.e. for the sample containing 3 parts out of 10 we have:

k = 2; N = 10 => N-k = 8; n = 3

Now, the lot is accepted if no defective component is found from the sample, thus, we assume
that 0 defective parts were selected from the 2 while 3 non-defective parts were selected from
the sample, with a total of selecting 3 parts from 10 i.e. we have:

P ( X=0 ) = (❑k C x ¿ N − k C n − x)/(❑10 C 3) = ❑2 C 0∗8C 3 / 120 = 56/120 = 0.4667 => 46.67%

This indicates that a sample containing 2 defective parts and 8 non-defective parts would be
accepted 46.67% of the time, which indicates that the system is faulty.

Example 5.9:
For 1 defective found in the sample for total of 3 defective in the sample, then we have to select
4 components from the remaining 37 non-defective components in the sample. As for total, 5
components out of 40 are to be selected, thus, we have for the hypergeometric distribution:

k = 3; x = 1; N = 40; n = 5
P ( X=1 ) = (❑k C x ¿ N − k C n − x)/❑40 C 5 = ❑3 C 1∗37 C4 / 658008 = 0.3011

Example 5.10:
For the given case, we have:

For 3 defective found in the sample for total of 12 defectives, then we have to select the other 7
for the sample as non-defective from a total of 88 non-defectives. Overall the probability will be
given for selecting 10 random components from a total of 100. Using hypergeometric
distribution, we have:

k = 12; x = 3; n = 10; N = 100

b ( x :N ,n , k ) = (❑k C x ¿ N − k C n − x) / (❑100 C10 ) = (❑12 C 3 ¿ 88 C7 ) / (❑100 C10 ) = 0.0807

Example 5.11:
For the case of Example 5.9, we have:

N = 40; n = 5; k = 3; x = 1

We have:

Mean = μ = nk/N = (5)(3)/(40) = 0.375

Variance = σ 2 = (N - n)/(N - 1) ¿ nk/N ¿ (1 - k/N) = (40 - 3)/(40 - 1) ¿ (5)(3)/(40) ¿ (1 - (3)/(40)) =

0.329

Example 5.12:
For the given case, we have to get the event that 3 of the tires are blemished out of total 1000,
then 7 tires would be un-blemished from a total of 4000 remaining. For the overall, 10 tires are
to be purchased from a total of 5000 whether they be blemish or not. Thus, for the
hypergeometric distribution, we have:

x = 3; k = 1000; N = 5000; n = 10

Now, we have:

P ( X=3 ) = (❑k C x ¿ N − k C n− x) / ❑5000 C10 = (❑1000 C3 ¿5000− 1000 C10 −3 ) / (❑5000 C10) = 0.2015

Example 5.13:
For the given case, we have:

A: Random variable representing people with blood type A

B: Random variable representing people with blood type B

O: Random variable representing people with blood type O

Now, we have to select a total of 5 people from the group of 10, where 2 people with A have to
be selected from a total of 4, 2 people with B have to be selected from a total of 3 and 1 person
with O has to be selected from a total of 3, thus, for the multivariate hypergeometric
distribution, we have:

a = 2; b = 2; o = 1; k a = 4; k b = 3; k o = 3; N = 10; n = 5

f ( a , b , o :k a , k b , k o , N , n ) = (❑k C a ¿k C b ¿ k C o) / (❑10 C 5) = (❑4 C2 ¿3 C2 ¿3 C1) / ❑10 C 5 = 0.2143

a b o

Exercises:
Exercise 5.29:
For the given case, we have to select a total of 6 bulbs from 9 bulbs in the box, where we have to
select 2 daffodil bulbs from a total of 4 and 4 tulip bulbs from a total of 5, thus, for the hyper
geometric distribution, we have:

k = 4; x = 2; n = 6; N = 9

P ( X=2 ) = (❑k C x ¿ N − k C n − x) / ❑9 C 6 = (❑4 C2 ¿9 − 4 C6 − 2) / ❑9 C 6 = 0.3571

Exercise 5.30:
For the given case, the custom officer has to select 3 tablets from a total of 15 tablets (6 narcotic
and 9 vitamin), where even if one of the tablets turns out to be from total of 6 narcotic tablets,
then the traveler will be arrested, thus, we have for the hyper geometric distribution, we have:

k = 6; n = 3; N = 15

P ( X ≥1 ) = 1 - P ( X=0 ) = 1 - b ( 0 :15 , 3 , 6 ) = 1 - (❑6 C 0 ¿15 −6 C3 − 0)/(❑15 C 3) = 1 - 0.1846 = 0.8154

Exercise 5.31:
Let X be the number of doctors on the committe then we have to select a total of 3 members
from 6 (4 doctors and 2 nurses). Thus, we have for our formula:

k = 4; n = 3; N = 6

P ( X=x ) = b ( x :N ,n , k ) = ❑4 C x ¿ 6 −4 C 3− x / ❑6 C 3 --(i)

Now, for given case, we have:

P ( 2≤ X ≤ 3 ) = P ( X=2 ) + P ( X=3 ) = (❑4 C2 ¿6 − 4 C3 − 2 / ❑6 C 3) + (❑4 C3 ¿6 − 4 C3 − 3 / ❑6 C 3) = 0.6 + 0.2

= 0.8

Exercise 5.32:
Let X be random variable representing the number of missiles fired, then we have to select x
non-defective from a total of 7 and the remaining 4-x defective from a total of 3 with overall
selection of 4 missiles from a lot of 10, we have using hypergeometric distribution:

k = 7; n = 4; N = 10
P ( X=x ) = b ( x :N ,n , k ) = ❑k C x ¿ N − k C n − x / ❑10 C 4 ---(i)

(a) For this case, we have:

P ( X=4 ) = ❑7 C 4 ¿10 −7 C 4 − 4 / ❑10 C 4 = 0.1667

(b) Let Y be the event that the missiles don't fire, then we have:

k = 3; n = 4; N = 10

P ( Y ≤ 2 ) = Σ 2y=0 b ( x : N , n , k ) = b ( 0 :10 , 4 ,3 ) + b ( 1 :10 , 4 , 3 ) + b ( 2 :10 , 4 , 3 ) = (❑3 C 0 ¿10 −3 C 4 − 0 /

10 C 4) + (❑3 C 1 ¿ 10− 3 C 4 − 1 / 10 C 4) + (❑3 C 2 ¿ 10− 3 C 4 − 2 / 10 C 4) = 0.1667 + 0.5 + 0.3 = 0.9667

Exercise 5.33:
For the given set of cards, we have to deal with 7 cards out of a total of 52 cards in the deck i.e:

n = 7; N = 52

(a) For 2 of them to exactly be face cards, we have to select 2 face cards from a total of 12 face
cards in the deck i.e. we have:

x = 2; k = 12;

Using hypergeometric distribution, we have:

P ( X=2 ) = b ( 2 :52 ,7 ,12 ) = ❑12 C 2 ¿52 −12 C 7 −2 / ❑52 C 7 = 0.3246

(b) For atleast one of them to be queen, we have to select 1 or more queens from a total of 4
queens in the deck i.e. we have:

x ≥ 1; k = 4

Using hyper geometric distribution, we have:

P ( X ≥1 ) = 1 - P ( X=0 ) = 1 - b ( 0 :52 , 7 ,12 ) = 1 - (❑12 C 0 ¿ 52−12 C7 − 0 / ❑52 C 7) = 1 - 0.1393

Exercise 5.34:
The waitress has to check 5 students from a total of 9 such that 4 of them are minors. For the
given case, the waitress will refuse exaclty two minors if and only if we have:

x = 2; k = 4; n = 5; N = 9

Using nyper geometric distribution, we have:

P ( X=2 ) = b ( 2 :9 , 5 , 4 ) = ❑4 C2 ¿9 − 4 C5 − 2 / 9 C 5 = 0.4762

Example 5.35:
For the given case, we have:

N = 50; k = 50 ¿ 20% = 10; n = 5; x ≤ 2

Using hyper geometric distribution, we have:

P ( X ≤2 ) = Σ 2x=0 b ( x : N , n , k ) = b ( 0 :50 , 5 ,10 ) + b ( 1 :50 ,5 , 10 ) + b ( 2 :50 , 5 ,10 ) = (❑10 C 0 ¿ 50− 10 C 5 −0

50 10 50 − 10 50 10 50 − 10 50
/ ❑ C 5) + (❑ C 1 ¿ C5 − 1 / ❑ C 5) + (❑ C 2 ¿ C 5− 2 / ❑ C 5) = 0.3106 + 0.4313 + 0.2098 =
0.9517

Exercise 5.36:
For the given case, 3 boxes are selected from a total of 25, i.e. we have:

N = 25; n = 3

(a) For a box to contain 3 defectives such that it is shipped, means that even though the box
contained defectives the checked components were not defective i.e. x = 0 while k = 3. Using
hyper geometric distribution, we have:

P ( X=0 ) = b ( x :N ,n , k ) = b ( 0 :25 , 3 , 3 ) = ❑3 C 0 ¿25 −3 C 3 −0 / ❑25 C 3 = 0.6695

(b) For a box to contain 1 defective such that it is send back for scanning, means that the
defective in the box was found regardless i.e. x = 1 and k = 1. Using hyper geometric distribution,
we have:

P ( X=1 ) = b ( x :N ,n , k ) = b ( 1 :25 , 3 ,1 ) = ❑1 C 1 ¿ 25− 1 C 3− 1 / ❑25 C 3 = 0.12

Exercise 5.37:
From the case in Exercise 5.36, now with the given conditon, the events of selecting boxes has
become independent of each other, thus, it has now become a case of binomail distribution, we
have:

n = 3; p = k/N

(a) For the first case, we have:

p = 3/25 = 0.12; q = 1 - p = 1 - 0.12 = 0.88; x = 0

P ( X=0 ) = b ( 0 :3 , 0.12 ) = ❑3 C 0 ¿ (0.12)❑0 ¿ (0.88)❑3 −0 = 0.6815

(b) For the second case, we have:

p = 1/25 = 0.04; q = 1 - p = 1 - 0.04 = 0.96; x = 1

P ( X=1 ) = b ( 1 :3 , 0.04 ) = ❑3 C 1 ¿ (0.04)❑1 ¿ (0.96)❑3 −1 = 0.1106

Exercise 5.38:
We have for the following case: (Since 10 out of total 150 are to be selected where 30 are
women)

N = 150; n = 10; k = 30

For binomial approximation, we have:

p = k/N = 30/150 = 0.2; q = 1 - p = 1 - 0.2 = 0.8

Now, we have for atleast 3 women to be selected:

P ( X ≥3 ) = 1 - P ( X ≤2 ) = 1 - Σ 2x=0 b ( x : n , p ) = 1 - (b ( 0 :10 , 0.2 ) + b ( 1 :10 , 0.2 ) + b ( 2 :10 , 0.2 )) = 1 -

(0.1074 + 0.2684 + 0.3019) = 1 - 0.6777 = 0.3223

Exercise 5.39:
We have for the following case: (Since 10 out of total 1200 residences are being selected where
half i.e 600 are in favour of being annexed)

N = 1200; n = 10; k = 600

For binomial approximation, we have:

p = k/N = 600/1200 = 1/2 = 0.5; q = 1 - p = 1 - 0.5 = 0.5

Now, we have for atleast 3 ni favour of annexure:

P ( X ≥3 ) = 1 - P ( X ≤2 ) = 1 - Σ 2x=0 b ( x : n , p ) = 1 - (b ( 0 :10 , 0.5 ) + b ( 1 :10 , 0.5 ) + b ( 2 :10 , 0.5 )) = 1 -

(0.00098 + 0.00976 + 0.0439) = 1 - 0.05464 = 0.9453

Exercise 5.40:
We have for the following case: (Since 15 votes are to be selected from a total of 10000, where
4000 are against the new sales tax and 6000 are in favour)

N = 10000; n = 10; k = 6000

For the binomial approximation:

p = k/N = 6000/10000 = 0.6; q = 1 - p = 1 - 0.6 = 0.4

Now, for at most 7 to votes in favour, we have:

P ( X ≤7 ) = 1 - P ( X ≥ 8 ) = 1 - Σ 10
x=8 b ( x : n , p ) = 1 - (b ( 8 :10 , 0.6 ) + b ( 9 :10 , 0.6 ) + b ( 10 :10 , 0.6 ) ) = 1 -
(0.1209 + 0.0403 + 0.0060) = 1 - 0.1672 = 0.8328

Exercise 5.41:
We have for the following case: (Since 18 seniors are to be selected from a total of 17000 where
70% disapprove to daily pot smoking)

N = 17000; n = 18; k = 17000 ¿ 70% = 11900

For the binomial approximation:

p = k/N = 11900/17000 = 0.7

Now, for more than 9 but fewer than 14 students to disaaprove daily pot we have:

P ( 9< X < 14 ) = Σ 13
x=10 b ( x :n , p ) = b ( 10 :18 , 0.7 ) + b ( 11:18 , 0.7 ) + b ( 12 :18 , 0.7 ) + b ( 13 :18 , 0.7 ) =
0.0811 + 0.1376 + 0.1873 + 0.2017 = 0.6077
Exercise 5.42:
To deal a bridge, we need to select 13 cards from a total of 52 cards. For the given case, we must
select 5 spades from a total of 13, 2 hearts from a total of 13, 3 diamonds from a total of 13 and 3
clubs from a total of 13, hence, we have for the multi-hyper geometric distribution:
x 1 = 5; x 2 = 2; x 3 = 3; x 4 = 3; k 1 = 13; k 2 = 13; k 3 = 13; k 4 = 13; n = 13; N = 52

We have:

f ( x 1 , x 2 , x3 , x 4 : N ,n , k 1 , k 2 , k 3 , k 4 ) = (❑13 C 5 ¿ 13 C2 ¿13 C 3 ¿13 C 3) / ❑52 C 13 = 0.0129

Exercise 5.43:
For the given case, we have: (values k 1 , k 2 , k 3 , k 4 represent Canadians, Japanese, Italian and
German respectively)
k 1 = 2; k 2 = 3; k 3 = 5; k 4 = 2; n = 4; N = 2 + 3 + 5 + 2 = 12

(a) For all nationalities to be represented their must be one student present from each country
i.e. we have:
x 1 = 1; x 2 = 1; x 3 = 1; x 4 = 1

Now, we have:

f ( x 1 , x 2 , x3 , x 4 : N ,n , k 1 , k 2 , k 3 , k 4 ) = (❑2 C 1 ¿ 3 C 1 ¿5 C 1 ¿2 C1 ) / ❑12 C 4 = 0.1212

(b) For all nationalities except Italian to be present, we have to have one of the following cases:

• 2 Canadians 1 Japanese 1 German

• 1 Canadian 2 Japanese 1 German
• 1 Canadian 1 Japanese 2 German

Hence, since its a matter of choice, we will apply addition rule to the multivariate
hypergeometric series, we have:

f ( 2 , 1 ,0 ,1 :12 , 4 , 2 ,3 , 5 , 2 ) + f ( 1 , 2 ,0 ,1 :12 , 4 , 2 ,3 , 5 , 2 ) + f ( 1 , 1 ,0 , 2 :12 , 4 , 2 ,3 , 5 , 2 ) = ((

2 3 5 2 12 2 3 5 2 12 2 3 5 2
❑ C 2 ¿ C 1 ¿ C 0 ¿ C 1) / ❑ C 4) + ((❑ C 1 ¿ C 2 ¿ C 0 ¿ C 1) / ❑ C 4) + ((❑ C 1 ¿ C 1 ¿ C 0 ¿ C 2) /
12
❑ C 4) = 0.01212 + 0.02424 + 0.01212 = 0.04848

Exercise 5.44:
For the given case, we have:

B: Random variable representing number of blue balls

R: Random variable representing number of red balls

G: Random variable representing number of green balls

Now, we have:
k b = 2; k r = 4; k g = 3; n = 5; N = 2 + 4 + 3 = 9

Now, for the given case, we have to have both blue balls and atleast 1 red ball i.e:

b = 2; r ≥ 1; g ≤ 2 (green balls are less than equal to 2 because out of the five balls given, 2 will be
blue which leaves us with 3 balls. The condition specifies that at least 1 ball would be red this
means that for the case of 1 red we will have 2 greens, for 2 reds we will have 1 green and for 3
reds we will have 0 greens)

P ( B=2 ; 1≥ R ≤3 ; G ≤ 2 ) = Σ 3r=1 f ( b , r , g :N ,n , k b , k r , k g ) = f ( 2 , 1 ,2 :9 , 5 , 2, 4 , 3 ) +
f ( 2 , 2 ,1 :9 , 5 , 2, 4 , 3 ) + f ( 2 , 3 , 0 :9 ,5 , 2 , 4 ,3 ) = ((❑2 C 2 ¿ 4 C1 ¿3 C2) / ❑9 C 5) + ((❑2 C 2 ¿ 4 C2 ¿3 C1) /
9 2 4 3 9
❑ C 5) + ((❑ C 2 ¿ C3 ¿ C0 ) / ❑ C 5) = 0.0952 + 0.1428 + 0.0317 = 0.2697

Exercise 5.45:
We are selecting 15 animals for our sample from a total of 25 animals, where 10 are tagged.
Now, for the sample to contain 5 tagged animals, we have:

x = 5; k = 10; n = 15; N = 25

Applying hypergeometric distribution, we have:

P ( X=5 ) = b ( 5 :25 , 15 ,10 ) = ❑10 C 5 ¿ 25− 10 C 15− 5 / ❑25 C 15 = 0.2315

Exercise 5.46:
We have to take 5 compressors for our sample from a total of 15 compressors in a given batch,
where 2 are faulty, thus, we have:

k = 2; n = 5; N = 15

(a) For the given case of having 1 faulty compressor in our sample, we have:

P ( X=1 ) = b ( 1 :15 ,5 , 2 ) = ❑2 C 1 ¿ 15− 2 C 5 −1 / ❑15 C 5 = 0.4762

(b) For the given case of discovering both the faulty compressors in our sample, we have:

P ( X=2 ) = b ( 2 :15 , 5 ,2 ) = ❑2 C 2 ¿ 15− 2 C 5 −2 / ❑15 C 5 = 0.0952

Exercise 5.47:
For the given case, we have a total of 20 firms from which 3 are in violation i.e. we have:

N = 20; k = 3

(a) For no violations to be caught for a sample of 5 firms, we have:

n = 5; x = 0

Using hyper geometric distribution, we have:

P ( X=0 ) = b ( 0 :20 , 5 , 3 ) = ❑3 C 0 ¿20 −3 C 5 − 0 / ❑20 C 5 = 0.3991

(b) For 2 violations to be caught for the above scenario, we have:

P ( X=2 ) = b ( 2 :20 , 5 ,3 ) = ❑3 C 2 ¿ 20− 3 C 5 −2 / ❑20 C 5 = 0.1316

Exercise 5.48:
For given case, we have to select 30 cans for our sample from a total of 10,000 cans, where 300
are underfilled i.e. we have:

N = 10000, n = 30; k = 300

For atleast one underfilled can, we have by the hyper geometric distribution:

P ( X ≥1 ) = 1 - P ( X=0 ) = 1 - b ( 0 :10000 , 30 , 300 ) = 1 - (❑300 C 0 ¿10000 − 300 C 30− 0 / ❑10000 C 30) = 1 - 0.4
= 0.6

Chapter 5 Section 3:
Examples:
Example 5.14:
For the given case, a team needs to win 4 matches in the series out of 7 to win the whole series.
For the given conditions of the teams, we have:

k = 4; p = 0.55; q = 1 - p = 1 - 0.55 = 0.45

(a) Now, we have for team A to win 6 series in the game:

P ( X=6 ) = b∗( x : k , p ) = b∗( 6 : 4 , 0.55 ) = ❑x −1 C k− 1∗pk ∗q x −k = ❑5 C 3 ¿ (0.55)❑4 ¿ (0.45)❑2 =

0.1853

(b) Now, we have for team A to win the series:

• Team A wins 4 matches

• Team A wins 5 matches
• Team A wins 6 matches
• Team A wins 7 matches

Since these all are possibilites, we can add up their probabilities to get the required probability:

P ( A w i n s S e r i e s ) = Σ 7x=4 b∗( x :k , p ) = b∗( 4 :4 ,0.55 ) + b∗( 5 :4 , 0.55 ) + b∗( 6 : 4 , 0.55 ) +

b∗( 7 : 4 , 0.55 ) = ❑4 − 1 C 4 −1 ¿ (0.55)❑4 ¿ (0.45)❑4 − 4 + ❑5 −1 C 4 − 1 ¿ (0.55)❑4 ¿ (0.45)❑5 −4 +
6 −1 7 −1
❑ C 4 − 1 ¿ (0.55)❑4 ¿ (0.45)❑6 −4 + ❑ C 4 − 1 ¿ (0.55)❑4 ¿ (0.45)❑7 −4 = 0.0915 + 0.1647 +
0.1853 + 0.1667 = 0.6082

(c) Now, we have for team A to win the playoffs, they must win atleast 3 out of 5 matches i.e. we
have: k = 3. This is possible if:
 • Team A wins 3 matches
• Team A wins 4 matches
• Team A wins 5 matches

Since these all are possibilities, we can add up their porbabilities to get the required probability:

P ( A w i n s P l a y − o f f s ) = Σ 5x=3 b∗( x :k , p ) = b∗( 3 :3 , 0.55 ) + b∗( 4 :3 , 0.55 ) + b∗( 5 :3 , 0.55 ) =

3 −1 4−1 5 −1
❑ C 3− 1 ¿ (0.55)❑3 ¿ (0.45)❑3 −3 + ❑ C 3 −1 ¿ (0.55)❑3 ¿ (0.45)❑4 − 3 + ❑ C 3− 1 ¿ (0.55)
❑ ¿ (0.45)❑ = 0.1663 + 0.224 + 0.2021 = 0.5924
3 5 −3

Example 5.15:
For the given case, let X be the random variable representing the first defective item found, then
we have:

x = 5; p = 1/100 = 0.01; q = 1 - p = 1 - 0.01 = 0.99

Now, using geometric distribution, we have:

P ( X=5 ) = p q x −1 = (0.01)(0.99)❑5 −1 = 0.0096

Example 5.16:
Let X represent the random variable representing the time when call was successful, thus ,we
have:

x = 5; p = 0.05; q = 1 - p = 1 - 0.05 = 0.95

Now, using the geometric distribution, we have:

P ( X=5 ) = p q x −1 = (0.05)(0.95)❑5 −1 = 0.0407

Example 5.17:
For the given case, we are given that within the specified time of 1 millisecond, 4 radioactive
particles pass the counter. Now for 6 particles to enter the counter, we have:
λ = 1; t = 4; x = 6
We have using Poisson distribution:

p ( x : λ t ) = e − λt ( λ t ) x /x ! = e❑− ( 1) (4 ) ¿ ((1)(4))❑6 / 6! = 0.1042

Example 5.18:
For the given case, the number of trucks arriving at the port on average is 10. The port can
handle at most 15 trucks per day. For the tankers to be turned away on a certain day would mean
that the number of tankers on that day were greater than 15 i.e. we have:
λ = 1; t = 10; => λ t = (1)(10) = 10; x > 15
We have using Poisson distribution:
P ( X >15 ) = 1 - P ( X ≤15 ) = 1 - Σ 15
x=0 p ( x : λ t ) = 1 - (p(0: 10) + p(1: 10) + p(2: 10) + p(3: 10) + p(4: 10) +
p(5: 10) + p(6: 10) + p(7: 10) + p(8: 10) + p(9: 10) + p(10: 10) + p(11: 10) + p(12: 10) + p(13: 10) + p(14:
10) + p(15: 10)) = 1 - (0.00004 + 0.00045 + 0.00227 + 0.00757 + 0.0189 + 0.0378 + 0.06306 +
0.09008 + 0.11259 + 0.12511 + 0.1137 + 0.09478 + 0.07291 + 0.05207 + 0.03472) = 1 - 0.82605 =
0.1739

Example 5.19:
For the given case, we have:

p = 0.005

(a) We have:

n = 400 => np = (400)(0.005) = 2

Now, for Possion distribution, we have:

P ( X=1 ) = p ( x :n p ) = p ( 1:2 ) = e❑−2 ¿ (2)^1 / 1! = 0.2706

(b) We have:

P ( X ≤3 ) = Σ 3x=0 p ( x :n p ) = p ( 0 :2 ) + p ( 1:2 ) + p ( 2:2 ) + p ( 3 :2 ) = (e❑−2 ¿ (2)^0 / 0!) + (e❑−2 ¿

(2)^1 / 1!) + (e❑−2 ¿ (2)^2 / 2!) + (e❑−2 ¿ (2)^3 / 3!) = 0.1353 + 0.2706 + 0.2706 + 0.1804 = 0.8569

Example 5.20:
For the given case, we have:

p = 1/1000 = 0.001; n = 8000; np = (8000)(0.001) = 8

6
Now, P ( X <7 ) = Σ x=0 p ( x :n p ) = p ( 0 :8 ) + p ( 1: 8 ) + p ( 2: 8 ) + p ( 3 :8 ) + p ( 4 : 8 ) + p ( 5: 8 ) + p ( 6 :8 ) =
(e❑−8 ¿ (8)^0 / 0!) + (e❑−8 ¿ (8)^1 / 1!) + (e❑−8 ¿ (8)^2 / 2!) + (e❑−8 ¿ (8)^3 / 3!) + (e❑−8 ¿ (8)^4 /
4!) + (e❑−8 ¿ (8)^5 / 5!) + (e❑−8 ¿ (8)^6 / 6!) = 0.0003 + 0.0027 + 0.0107 + 0.0286 + 0.0572 +
0.0916 + 0.1221 = 0.3132

Exercises:
Exercise 5.49:
We have for the given case:

X = 10; k = 5; p = 0.3; q = 1 - p = 1- 0.3 = 0.7

Now, we have:

b ( x :k , p ) = b ( 10 :5 , 0.3 ) = ❑10− 1 C 5 −1 ¿ (0.3)❑5 ¿ (0.7)❑10− 5 = 0.0514

Exercise 5.50:
Let X be random variable representing number of heads, then we have:
(a) For given case: X = 7; k = 3; p = 0.5; q = 0.5

b ( x :k , p ) = b ( 7 :3 , 0.5 ) = ❑7 −1 C 3 −1 ¿ (0.5)❑3 ¿ (0.5)❑7 −3 = 0.1172

(b) For given case: X = 4; k = 1; p = 0.5; q = 0.5

b∗( x : k , p ) = b∗( 4 :1 ,0.5 ) = ❑4 − 1 C 1− 1 ¿ (0.5)❑1 ¿ (0.5)❑4 − 1 = 0.0625

Exercise 5.51:
Let X be the random variable representing the number of tosses, then:

p = 3/4 = 0.75 ; q = 1 - p = 1 - 0.75 = 0.25; k = 1 (Since coin tosses stop on the first success)

Since, we want to determine the first success, we use the geometric distribution as:

P ( X < 4 ) = Σ 3x=1 g ( x ; p ) = g(1;0.75) + g(2;0.75) + g(3;0.75) = (0.75)(0.25)❑1 −1 + (0.75)(0.25)❑2 −1 +

(0.75)(0.25)❑3 −1 = 0.75 + 0.1875 + 0.0468 = 0.9843

Exercise 5.52:
Let X be the number of mice tested, then we have:

X = 8; k = 2; p = 1/6 = 0.1667; q = 1 - p = 1 - 1/6 = 0.8333

Now, we have:

b∗( x : k , p ) = b∗( 8 :2 , 0.1667 ) = ❑8 −1 C2 −1 ¿ (0.1667)❑2 ¿ (0.8333)❑8 −2 = 0.0651

Exercise 5.53:
Average number of production per day = λ t = 5

(a) We have:

P ( X >5 ) = 1 - P ( X ≤5 ) = 1 - Σ 5x=0 p ( x : λ t ) = 1 - (p(0:5) + p(1:5) + p(2:5) + p(3:5) + p(4:5) + p(5:5)) = 1

- (0.0067 + 0.0337 + 0.0842 + 0.1404 + 0.1755 + 0.1755) = 1 - 0.6161 = 0.3839

(b) We have:

P ( X=0 ) = p ( x : λ t ) = p(0:5) = e❑−5 = 0.0067

Exercise 5.54:
We have for the given case:

p = 2/3 ; q = 1 - 2/3 = 1/3; X = 5

(a) For the first prescription, we have: k = 1

b∗( x : k , p ) = b∗( 5 :1 ,2 /3 ) = ❑5 −1 C 1 −1 ¿ (2/3)❑1 ¿ (1/3)❑5 −1 = 0.0082

(b) For the third prescription, we have:

b∗( x : k , p ) = b∗( 5 :3 , 2/3 ) = ❑5 −1 C 3 −1 ¿ (2/3)❑3 ¿ (1/3)❑5 −3 = 0.1975

Exercise 5.55:
For the given case, we have:

p = 0.7; q = 1 - p = 1 - 0.7 = 0.3

(a) To pass on the third try, we have:

P ( X=3 ) = g ( 3 :0.7 ) = (0.7)(0.3)❑3 −1 = 0.063

(b) To pass before the fourth try, we have:

P ( X < 4 ) = Σ 4x=1 g ( x : p ) = g(1:0.7) + g(2:0.7) + g(3:0.7) = 0.7 + 0.21 + 0.063 = 0.973

Exercise 5.56:
Average number of accidents per month = λ t = 3

(a) For given case:

P ( X=5 ) = p ( 5: 3 ) = e❑−3 ¿ (3)❑5/5! = 0.1008

(b) For given case:

P ( X <3 ) = Σ 2x=0 p ( x : λ t ) = p(0:3) + p(1:3) + p(2:3) = 0.0497 + 0.1493 + 0.2240 = 0.4230

(c) For given case:

P ( X ≥2 ) = 1 - P ( X <2 ) = 1 - Σ 1x=0 = 1 - (p(0:3) + p(1:3)) = 1 - (0.0497 + 0.1493) = 1 - 0.199 = 0.801

Exercise 5.57:
Average number of errors = λ t = 2

(a) For the given case, we have:

P ( X ≥ 4 ) = 1 - P ( X < 4 ) = 1 - Σ 3x=0 p ( x : λ t ) = 1 - (p(0:2) + p(1:2) + p(2:2) + p(3:2)) = 1 - (0.1353 +

0.2706 + 0.2706 + 0.1804) = 1 - 0.8569 = 0.1431

(b) For the given case, we have:

P ( X=0 ) = p ( 0 :2 ) = e❑−2 = 0.1353

Exercise 5.58:
Averge number of hurricanes = λ t = 6

(a) We have for given case:

P ( X < 4 ) = Σ 3x=0 p ( x : λ t ) = p(0:6) + p(1:6) + p(2:6) + p(3:6) = 0.0025 + 0.0148 + 0.0446 + 0.0892 =
0.1511
(b) We have for given case:

P ( 6 ≤ X ≤ 8 ) = Σ 8x=6 p ( x : λ t ) = p(6:6) + p(7:6) + p(8:6) = 0.1606 + 0.1377 + 0.1032 = 0.4015

Exercise 5.59:
For the given case, we have:

p = 0.8, q = 1 - p = 1 - 0.8 = 0.2

(a) For the given case, we have: x = 6, k = 4

b∗( x : k , p ) = b∗( 6 : 4 , 0.8 ) = ❑6 −1 C4 −1 ¿ (0.8)❑4 ¿ (0.2)❑6 −4 = 0.1638

(b) For the given case, we have: x = 3, k = 1

b∗( x : k , p ) = b∗( 3 :1 , 0.8 ) = ❑3 −1 C 1 −1 ¿ (0.8)❑1 ¿ (0.2)❑3 −1 = 0.032

Exercise 5.60:
Estimated number of mice per acre = μ = 12

(a) For the given case:

P ( X <7 ) = Σ 6x=0 p ( x : μ ) = p(0:12) + p(1:12) + p(2:12) + p(3:12) + p(4:12) + p(5:12) + p(6:12) = 0.0458

(b) For the given case: x = 3, k = 2, p = Probability per Acre = 0.0458, q = 1 - p = 1 - 0.0458 =
0.9542

b∗( x : k , p ) = b∗( 3 :2 , 0.0458 ) = ❑3 −1 C 2 −1 ¿ (0.0458)❑2 ¿ (0.9542)❑3 −2 = 0.004

Exercise 5.61:
For the given case, we have:

p = 1/1000 = 0.001; n = 10,000; np = (10,000)(0.001) = 10

Now,

P ( X =6|X =7 ) X=8 ) = P ( X=6 ) + P ( X=7 ) + P ( X=8 ) = p(6:10) + p(7:10) + p(8:10) = 0.063 + 0.09
+ 0.1126 = 0.2656

Exercise 5.62:
We have for the given case:

p = 0.004; n = 1875; np = (1875)(0.004) = 7.5

(a) For the given case:

P ( X <5 ) = Σ 4x=0 p ( x :n p ) = p(0:7.5) + p(1:7.5) + p(2:7.5) + p(3:7.5) = 0.132

(b) For the given case:

P ( X =8|X =9 ) X=10 ) = P ( X=8 ) + P ( X=9 ) + P ( X=10 ) = p(8:7.5) + p(9:7.5) + p(10:7.5) = 0.1373
+ 0.1144 + 0.0858 = 0.3375

Exercise 5.63:
We have:

Mean = μ = Average number of hurricanes = 6 Variance = σ 2 = Expected value = Mean = 6

Exercise 5.64:
We have:

Mean = μ = np = 10 Variance = σ 2 = Expected value = Mean = 10

Exercise 5.65:
Average number of cars per year = λ t = (5)(1) = 5

(a) For the given case, we have:

P ( X ≤3 ) = Σ 3x=0 p ( x : λ t ) = p(0:5) + p(1:5) + p(2:5) + p(3:5) = 0.0067 + 0.0337 + 0.0842 + 0.0034 =

0.128

(b) For the given case, we have:

P ( X >1 ) = 1 - P ( X <1 ) = 1 - Σ 1x=0 p ( x : λ t ) = 1 - (p(0:5) + p(1:5)) = 1 - (0.0067 + 0.0337) = 1 - 0.0404

= 0.9596

Exercise 5.66:
Average arrival of aircrafts per hour = μ = 6t = 6(1) = 6

(a) For the given case, we have:

P ( X=4 ) = p ( 4 : 6 ) = e❑−6 ¿ 6❑4 / 4! = 0.1338

(b) For the given case, we have:

P ( X ≥ 4 ) = 1 - P ( X < 4 ) = 1 - Σ 3x=0 p ( x : μ ) = p(0:6) + p(1:6) + p(2:6) + p(3:6) = 0.0025 + 0.0148 +

0.0446 + 0.0892 = 0.1511

(c) For given case, we have: t = 12

μ = 6t = 6(12) = 72
Now,

P ( X ≥75 ) = 1 - P ( X ≤74 ) = 1 - Σ 74
x=0 p ( x : μ ) = 1 - 0.6227 = 0.3773
Exercise 5.67:
Average number of arrivals = μ = 7t For two-hour period: μ = 7(2) = 14

(a) For the given case, we have:

P ( X >10 ) = 1 - P ( X ≤10 ) = 1 - Σ 10
x=0 p ( x : μ ) = 1 - 0.1757 = 0.8243

(b) For the given case, we have:

Mean arrivals = μ = 14

Exercise 5.68:
Mean number of students who failed test = np = (1875)(0.004) = 7.5

Exercise 5.69:
We have:

p = 0.001; n = 400 Mean = μ = np = (400)(0.001) = 0.4

Exercise 5.70:
We have for the given case of binomial distribution:

p = Probability of being defective = 1% = 1/100 = 0.01; n = 100

(a) Mean = μ = np = (100)(0.01) = 1

(b) Variance = σ 2 = np(1-p) = (100)(0.01)(1-0.01) = 0.99

Exercise 5.71:
Mean number of flaws = μ = λ t = (1.5)(5) = 7.5

For the given case, we have:

P ( X=0 ) = p ( 0 :7.5 ) = e❑−7.5 = 0.000553

Exercise 5.72:
Potholes per mile = λ = 2

(a) For the given case, we have:

P ( X ≤1 ) = P ( X=0 ) + P ( X=1 ) = p(0:2) + p(1:2) = 0.1353 + 0.2707 = 0.406

(b) For the given case, we have:

For 5 miles, we have: μ = λ t = (2)(5) = 10

P ( X ≤ 4 ) = Σ 4x=0 p ( x : μ ) = p(0:10) + p(1:10) + p(2:10) + p(3:10) + p(4:10) = 0.0292

Exercise 5.73:
Average emergencies per hour = λ = 5

(a) For the given case, we have:

μ = λ t = (5)(1) = 5

P ( X >10 ) = 1 - P ( X <10 ) = 1 - Σ 10
x=0 p ( x : μ ) = 1 - 0.9863 = 0.0137

(b) For the given case, we have:

μ = λ t = (5)(3) = 15

P ( X >20 ) = 1 - P ( X <20 ) = 1 - Σ 20
x=0 p ( x : μ ) = 1 - 0.9170 = 0.083

Exercise 5.74:
We have for the given geometric distribution:

p = 3% = 0.03; q = 1 - p = 1 - 0.03 = 0.97

(a) For the 15 people to pass succesfully so that the 16th is caught, we have:

P ( X=16 ) = g ( 16 :0.03 ) = (0.03)(0.97)❑16− 1 = 0.0189

(b) For the expected number of people, we have:
μ = 1/p = 1/0.03 = 33.33

Exercise 5.75:
We have for the given geometric distribution:

p = 0.10; q = 1 - p = 1 - 0.10 = 0.9

Now, since the robot fails during its 6th shift, we have:

P ( X ≤6 ) = Σ 6x=1 g ( x : p ) = g(1:0.1) + g(2:0.1) + g(3:0.1) + g(4:0.1) + g(5:0.1) + g(6:0.1) = 0.1 + 0.09 +

0.081 + 0.0729 + 0.06561 + 0.059049 = 0.4685