Adithya Giridharan

Question No.1
A satellite system consists of 4 components and can func-
tion adequately if at least 2 of the 4 components are
in working condition. If each component is, indepen-
dently, in working condition with probability .6, what is
the probability that the system functions adequately?
In [3]:
import math
p = 0.6
q = 0.4
def combination(m,n):
return math.factorial(m)/(math.factorial(m-n)*math.factorial(
In [4]:
print("Probability for 2 components working")
P2 = combination(4,2)*pow(p,2)*pow(q,2)
print(P2)
Probability for 2 components working
0.3456000000000001
In [5]:
print("Probability for 3 components working")
P3 = combination(4,3)*pow(p,3)*pow(q,1)
print(P3)
Probability for 3 components working
0.34559999999999996
In [6]:

1
print("Probability for 4 components working")
P4 = combination(4,4)*pow(p,4)*pow(q,0)
print(P4)
Probability for 4 components working
0.1296
In [7]:
print("System functions adequately")
print(P2+P3+P4)
System functions adequately
0.8208
In [ ]:

2
 Aditi Rai
Question No.2
A communications channel transmits the digits 0
and 1. However, due to static, the digit trans-
mitted is incorrectly received with probability .2.
Suppose that we want to transmit an important
message consisting of one binary digit. To reduce
the chance of error, we transmit 00000 instead of
0 and 11111 instead of 1. If thereceiver of the
message uses ” majority” decoding, what is the
probability that the message will be incorrectly
decoded? What independence assumptions are
you making? (By majority decoding we mean
that the message is decoded as ” 0” if there are
at least three zeros in the message received and
as ” 1” otherwise.)

Solution : To reduce the chance of error, we trans-

mit 00000 instead of 0 and 11111 instead of 1. The digit
transmitted is incorrectly received with the probability
of 0.2. We are interested in probability of message being
wrong when decoded. Receiver uses majority decoding.
So, if 11111 is transmitted it will be correctly received if
there are atleast 3 number 1. Let X count occurrence of
number 1 in the code. Therefore, we have:

5 3 5 4 5 5
. 455 + . 455 + . 455




P ( X >= 3 ) = 3 4 5

45 +5.44 +10.43 2944

P ( X >= 3 ) = 55 = 55 = 0.94208

3
 Obviously P ( X <= 2 ) = 1 - P ( X >= 3 ) = 0.05792.

Same caculations hold for the case when 00000 is trans-

mitted. We are interested in the probability of a random
message to be incorrectly decoded. Let Y be initial mes-
sage. Also, let A be an event message is wrongly decoded.
Then we have:

P (A) = P(A/Y=00000)P(Y=00000) + P(A/Y=11111)P(Y=11111)

1
P (A) = 0.05792 . 2 . 2 = 0.05792 (ANS)

4
 Ashish Bhatia
Question No.3
If each voter is for Proposition A with probabil-
ity .7, what is the probability that exactly 7 of 10
voters are for this proposition?

Solution:
here p=0.7 probability that exactly 7 of 10 voters are for
this proposition =
 
10
.77 .33 = .2668
7

5
 Rishita Srivastava
Question No.4
Suppose that a particular trait (such as eye color
or left-handedness) of a person is classified on the
basis of one pair of genes, and suppose that d rep-
resents a dominant gene and r a recessive gene.
Thus, a person with dd genes is pure dominance,
one with rr is pure recessive, and one with rd is
hybrid. The pure dominance and the hybrid are
alike in appearance. Children receive 1 gene from
each parent. If, with respect to a particular trait,
2 hybrid parents have a total of 4 children, what
is the probability that 3 of the 4 children have
the outward
appearance of the dominant gene?

Solution:
d=dominant trait
r=recessive trait
where,
dd= Pure dominant
rr= Pure recessive
rd=dr=Hybrid
Given that the parents are hybrid and each child gets
one gene from each parent.
Parent 1: r d
Parent 2: r d
Possible genes for the children-
rr, rd, dr, dd
Now it is givent that hybrid and dominant traits have

6
the same outward appearance.
Therefore, dd, rd and dr have the same outward appear-
ance.

P(dominant appearance)= 43
P(non dominant appearance)= 41
For 3 out of 4 children to be have outward appearance
of dominant trait:

4 3
∗ ( 34 ) ∗ 1


3 4 =0.4218

7
 Ashish Kumar Sharma
Question No.5
5. At least one-half of an airplane’s engines are required
to function in order for it to operate. If each engine inde-
pendently functions with probability p, for what values
of p is a 4-engine plane more likely to operate than a
2-engine plane?

Solution: It is given that at least one half of an airplane’s

engine is required to function in order for it to operate
.Since each engine is assumed to fail or work indepen-
dently of what happens with the other engine,it follows
that the number of engines remaining operative is a bi-
nomial random variable.
Hence, the probability that a four engine plane makes a
successful flight is,
P(4-engine plane) = 4C2 p2 (1 − p)2 + 4C3 p3 (1 − p)1 +
4C4 p4 (1 − p)0
4! 4! 4!
= p2 + p3 + p4
2! (4 − 2)! 3! (4 − 3)! 4! (4 − 4)!
= 6p2 (1 − p)2 + 4p3 (1 − p) + p4
P(2-engine plane) = 2C1 p(1 − p) + 2C2 p2 (1 − p)0
= 2p (1 − p) + p2
The four Engine plane will be safer than the two-Engine
plane when,
P(4-Engine plane) ≥ P(2−Engine plane)
This implies the value of p for which four-engine plane
will be safer is,
=⇒ 6p2 (1 − p)2 + 4p3 (1 − p) + p4 ≥ 2p (1 − p) + p2

8
=⇒ 6p2 (1 − p)2 + 4p3 (1 − p) + p4 − 2p (1 − p) − p2 ≥ 0
After solving this equation, we get:
=⇒ (p − 1)2 (3p − 2) ≥ 0
=⇒ (3p − 2)≥ 0 (Since
2
(p-1) ≥ 0)
=⇒ p≥ 2/3
Hence, the four engine plane is safer when the engine
success probability is at least as large as 2/3 , where as
the two-engine plane is safer when the probability falls
below 2/3.

9
 Harendra Singh
Question No.6
Question 6 : Let X be a binomial random variable with

E(X) = 7 and V ar(X) = 2.1

Find
(a) P X = 4
(b) P X = 12

Answer :
Given,

E(X) = 7

V ar(X) = 2.1

Now,

E(X) = np = 7

V ar(X) = 2.1

np(1 − P ) = 2.1

10
 7(1 − P ) = 2.1

1 − P = 0.3

P = 0.7

Substituting P = 0.7 in E(X) = 7

np = 7

n × 0.7 = 7

n = 10

(a) : Probability X=4,

 
n
P (X = 4) = x px (1 − P )n−x
C

 
10
= 4 (0.7)4 (1 − 0.7)6
C

11
 = 210 × 0.2401 × 0.000729

= 0.0368

(b) : Probability X=12,

P (X = 12) = 0

Since X can not be more than n.

12
 Prakhar Agrawal
Question No.7
If X and Y are binomial random variables with respec-
tive parameters (n, p) and (n, 1 − p), verify and explain
the following identities:
P{X ≤ i} = P{Y ≥ n − i};
(b) P{X = k} = P{Y = n − k}.

Solution:
a):
P{X ≤ i} = P{Y ≥ n-i}
L.H.S: P{X ≤ i} = n0 p0 (1 − p)n + n1 p1 (1 − p)n−1 +

. . . . . . . . . . + ni pi (1 − p)n−i


     
n n−0 n n−1 n
= 0
p (1 − p) + 1
p (1 − p) +. . . .+ pi (1 − p)n−i
n−0 n−1 n−i
Because nx = n−x n



     
n n n
= (1 − p)n−0 p0 + 1 − p)n−1 p1 +. . . .+ (1 − p)n−i pi
n−0 n−1 n−i
   
n n
= (1 − p)n−0 pn−(n−0) +. . . .+ (1 − p)n−i pn−(n−i)
n−0 n−i
= P{Y ≥ n-i} = RHS

13
b):

P{X = k} = P{Y = n −
k}.

L.H.S: P{X = k} = nk pk (1 − p)n−k
 
n
= pk (1 − p)n−k
n−k
= P{Y = n − k}.

14
 Akshay Kumar
Question No.8
QUES.8
If X is a binomial random variable with parameters n
and p, where 0 < p < 1, show that
p
(a) P(X = k + 1) = 1−p × n−k
k+1 ×P (X = k), k = 0, 1, ....., n−
1

(b) As k goes from 0 to n, P(X = k) first increases and

then decreases, reaching its largest value when k is the
largest integer less than or equal to the (n + 1)p.

(a). Ans
p n−k
P(X= k+1) = 1−p × k+1 P (X = k), k = 0, 1, ......, n − 1

L.H.S :
n

k+1
P (X = k + 1) = k+1 ×p × (1 − p)n−k−1
n!
= (k+1)!(n−k−1)! × p × pk × (1 − p)n−k × (1 − p)−1

n! p
= k!(k+1)!(n−k−1)! × 1−p × (p)k × (1 − p)n−k

n−k p n!
= k+1 1−p (k)!(n−k)! × pk × (1 − p)n−k

n−k p n


= k+1 1−p × k ×pk × (1 − p)n−k : R.H.S

15
 (b). Ans:-

P(X= k+1) ≥ P (X = k)

p n−k
= 1−p k+1 P (X = k) ≥ P (X = k)

= p(n-k) ≥ (1 − p)(k + 1)

= p(n − k + k + 1) ≥ k + 1

= p(n + 1) ≥ k + 1

k+1
=p≥ n+1

16
 As long as p(n + 1) is greater than (k + 1) , P(X)=k
is less than PX=k+1, and the distribution function is
increasing. But if k is the largest integer less than or
equal to (n + 1)p, then (n + 1)p is greater than k+ 1,
and the distribution function is decreasing for this and
all greater values of k.

17
 Kaveti Pavan
Question No.9
Derive the moment generating function of a bi-
nomial random variable and then use your result
to verify the formulas for the mean and variance
given in the text.

solution:

The moment generating function

ϕ (t) of the random variable X is defined for all
values t by:

  X tX
ϕ (t) = E etX = e p (x)
x
probability function in case of binomial distribution is
P (X = x) = nC x px (1 − p)n−x
X
ϕ (t) = C x px (1 − p)n−x etX
n
X
x
= C x pet (1 − p)n−x
n

n
= pet + 1 − p
d  
ϕt (t) = E etX
dt

d
n

ϕt (t) = pet + 1 − p
dt

n−1 t
= n pet + 1 − p pe

18
 N ow,

n−1
ϕt (0) = E (X) = n pe0 + 1 − p pe0 = np (p + 1 − p) = np
Hence, E (X) = np
d
ϕn (t) = ϕt (t)
dt
d 
t

n−1 t 
= n pe + 1 − p pe
dt

n−2 2 t
n−1
= n (n − 1) pet + 1 − p p e +pet n pet + 1 − p
ϕn (0) = E X 2 = n (n − 1) p2 (p + 1 − p)+pn (p + 1 − p) = np (1 − p)

Hence,
V ar (X) = ϕn (0)−ϕt (0)2 = n (n − 1) p2 +np−n2 p2 = np (1 − p)
E (X) = npandV ar (X) = np (1 − p)

19
 Umar Abdullah
Question No.10
Question: Compare the Poisson approximation with
the correct binomial probability for the following cases:
(a) P (X = 2) when n = 10, p = .1;
(b) P (X = 0) when n = 10, p = .1;
(c) P (X = 4) when n = 9, p = .2.
Solution:
(a) Binomial Probability:
P (X = 2) = 10

2 8
2 ∗ (0.1) ∗ (0.9) = 0.1937
Poisson approximation:
λ = n ∗ p = 10 ∗ 0.1 = 1
2 −1
P (X = 2) = (1 )(e
2!
)
= 0.1839
(b) Binomial Probability:
P (X = 0) = 10

0 10
0 ∗ (0.1) ∗ (0.9) = 0.3487
Poisson approximation:
λ = n ∗ p = 10 ∗ 0.1 = 1
0 −1
P (X = 0) = (1 )(e
0!
)
= 0.3678
(c) Binomial Probability:
P (X = 4) = 94 ∗ (0.2)4 ∗ (0.8)5 = 0.0661

Poisson approximation:
λ = n ∗ p = 9 ∗ 0.2 = 1.8
4 −1.8
P (X = 4) = (1.8 )(e
4!
)
= 0.0723

20
 Amit Kumar Behera
Question No.11
We buy lottery tickets in 50 lotteries , in each of which
1
chance of winning prize is 100 . what is the (approximate)
probability that you will win a prize (a) at least once, (b)
exactly once, and (c) at least twice?

Solution:
Number of trials=50
Probability of winning prize =1/100, which is small
1
Using Poisson model λ = n × p = 50 × 100 = 0.5
1. P (X ≥ 1) = 1 − P (X = 0)
= 1 − e−0.5
= 0.393
e−0.5 × 0.51
2. P (X = 1) = 1!

= 0.303

3. P (X ≥ 2) = 1 − [P (X = 0) + P (X = 1)]
= 1 − [e−0.5 + 0.5 e−0.5 ]
= 0.0892

21
 Sambodhi Sengupta
Question No.12

1 Question No 12

The number of times that an individual contracts a cold

in a given year is a Poisson random variable with param-
eter = 3. Suppose a new wonder drug (based on large
quantities of vitamin C) has just been marketed that re-
duces the Poisson parameter to = 2 for 75 percent of the
population. For the other 25 percent of the population,
the drug has no appreciable effect on colds. If an indi-
vidual tries the drug for a year and has 0 colds in that
time, how likely is it that the drug is beneficial for him
or her?

Solution: Let A1 be the event that the drug is beneficial

and A2 be the event that the drug is not beneficial. Let

22
B be the event that the individual has no cold. Given:
λ1 = 3
λ2 = 2
P (B | A1 ) = 0.75
P (B | A2 ) = 0.25
P (A1 )P (B|A1 )
P (A1 | B) = P (A1 )P (B|A 1 )+P (A2 )P (B|A2 )
λ0
e−λ2 1
0! ×0.75
= λ 0 λ0
e−λ2 0!2 ×0.75+e−λ1 0!1 ×0.25
−2
e ×0.75
= e−2 ×0.75+e−3 ×0.25
0.75
= 0.75+0.25e −1
1
= 1+1/3e
3e
= 1+3e

23
 Medha Misra
Question No.13
In the 1980s, an average of 121.95 workers died on
the job each week. Give estimates of the following
quantities:
1. the proportion of weeks having 130 deaths or
more
2. the proportion of weeks having 100 deaths or
less
Explain your reasoning.

Answer 13.
i
Given, P(X = i) ≈ e−λ λi! and λ = 121.95
Let ’X’ be the proportion of weeks having deaths
i
−121.95 (121.95)
1. P(X ≥ 130) ≈ 1 - 129
P
i=0 e i!
i
−121.95 (121.95)
2. P(X ≤ 100) ≈ 100
P
i=0 e i!

24
 Asif Raza
Question No.14
Approximately 80,000 marriages took place in the state
of New York last year. Estimate the probability that for
at least one of these couples (a) both partners were born
on April 30; (b) both partners celebrated their birthday
on the same day of the year. State your assumptions.

Solution:
(a). Probability that both partners have same birthday
1
= 365 1
* 365 = 7.51 ∗ 10− 6
Since, probability is very small, we assume poisson’s ap-
proximation.
λ = np
⇒ λ = 80000 ∗ 7.51 ∗ 10− 6 = 0.6
Let X denotes numbers of couple having birthday on
April 30.
P(X ≥ 1) = 1 − P (X = 0)
= 1 - 0.60 ∗ e− 0.6/0!
= 1 - (e− 0.6) = 0.451

(b). To have birthday on same day of the year, P(same

1 1 1
birthday) = 365 * 365 * 365 = 365
Again, use poisson distribution λ = np
1
= 80000 * 365 = 219.2

P(X ≥ 1) = 1 − P (X = 0)
0 (
= 1 - 219.2 ∗e0!−219.2) ≈ 1

25
 Inzamam Safi
Question No.15
Question: The game of frustration solitaire is played
by turning the cards of a randomly shuffled deck of 52
playing cards over one at a time. Before you turn over
the first card, say ace; before you turn over the second
card, say two, before you turn over the third card, say
three. Continue in this manner (saying ace again before
196 Chapter 5: Special Random Variables turning over
the fourteenth card, and so on.) You lose if you ever turn
over a card that matches what you have just said. Use
the Poisson paradigm to approximate the probability of
winning. (The actual probability is .01623.)
Solution:

When we shuffle the cards after each turn (as said

in the given problem), then the number of hits has the
binomial distribution, n = 52. probability of hits on any
trial is 1/13.
The binomial distribution with n large p small, np
modest is well approximated by the Poisson with pa-
rameter = np. Here, np 4 and the probability that a
Poisson with parameter = np =
1 ∗ 52
13
=4
takes the value 0 is e−4 .

Thus, the approximate probability of winning is e−4 .

26
 Arjit Kumar
Question No.16
QUESTION 16 The probability of error in the transmis-
sion of a binary digit over a communication channel is
1/1000. Write an expression for the exact probability of
more than 3 errors when transmitting a block of 1000
bits. What is its approximate value? Assume indepen-
dence.

Solution:

Let X be the number of errors

Probability of error, p = 1/1000
Number of trials,n = 1000

Probability of more than 3 errors ,

P(X≥ 3) = 1 − P (X < 3)

= 1 − (P (X = 0) + P (X = 1) + P (X = 2))

1000 1000

0 1000

1 999
= 1−( 0 .(0.001) .(0.999) + 1 .(0.001) .(0.999) +
1000 1000

2 998


2 .(0.001) .(0.999) ) + 3 .(0.001)3 .(0.999)997 )

= 1 - 0.92005963507

= 0.7994036492

27
 Md Ahmad Jami
Question No.17

If X is a Poisson random variable with mean λ, show

that P(X = i ) first increases and then decreases as i in-
creases, reaching its maximum value when i is the largest
integer less than or equal to λ.

Solution:

X is a Poisson random variable with mean λ

i
−λ λ
P (X = i) = e
i!

−λ λi−1
P (X = i − 1) = e
(i − 1)!
So,
i
P (X = i) e−λ λi! λ
r= = λ i−1 =
P (X = i − 1) e−λ (i−1)! i

So, P(X = i - 1) increases as i increases till it reaches λ

since the ratio r decreases. So, P(X = i - 1) is maximum
when i = λ. After reaching λ, if i increases then P(X
= i - 1) decreases since the ratio r becomes less than 1

28
 Uditanshu Gupta
Question No.18
A contractor purchases a shipment of 100 tran-
sistors. It is his policy to test 10 Of these tran-
sistors and to keep the shipment only if at least
9 of the 10 are in Working condition. If the ship-
ment contains 20 defective transistors, what is
the Probability it will be kept?

Solution:-
(N ) ( M )
Given that: P{ X = i} = i N +Mn−i
( n )
Given: n=10

Working transistor = N = 80
Defective transistors = M = 20
Let i be the number of working transistors.
Probability that X ≥ 9
P (X ≥ 9) = P (X = 9) + P (X = 10)

( ) (
80 20
) ( 80
10 ) ( 20
10−10 )
P (X ≥ 9) = 9 10−9
+
( 100
10 ) ( 100
10 )
231900297200∗20 1646492110120
P (X≥ 9) = 17310309456440 + 17310309456440

P (X≥ 9) = 0.268 + 0.095

P (X ≥ 9) = 0.363

29
 Adithya Giridharan
Question No.19
Let X denote a hypergeometric random variable with pa-
rameters n, m, and k. That is, P{X=i} = (nCi)*(mCk-
i)/(n+mCk) , i = 0, 1, . . . , min(k, n) (a) Derive a
formula for P{X = i} in terms of P{X = i 1}. (b) Use
part (a) to compute P{X = i} for i = 0, 1, 2, 3, 4, 5 when
n = m = 10, k = 5, by starting with P{X = 0}. (c) Based
on the recursion in part (a), write a program to compute
the hypergeometric distribution function. (d) Use your
program from part (c) to compute P{X 10} when n =
m = 30, k = 15.
In [4]:
import math
import array as arr
def combination(a,b):
return math.factorial(a)/(math.factorial(a-b)*math.factorial(
P{X=i} in terms of P{X=i-1} P{X=0} = mCk / (n+m)Ck
{base case} P{X=i} = ((n-i+1)/i)((k-i+1)/(m-k+i))P{X=i-
1} for any i not equal to 0
In [8]:
P_i = arr.array(’f’)
n = 10
m = 10
k = 5
i = min(k,n)
for x in range(i+1):
if x==0:
P_i.insert(x,combination(m,k)/combination(n+m,k))

30
 else:
alpha = (n-x+1)/x
beta = (k-x+1)/(m-k+x)
P_i.insert(x,alpha*beta*P_i[x-1])
print("P{X = i} i from 0 to 5 values")
print(P_i)
P{X = i} i from 0 to 5 values
array(’f’, [0.016253869980573654, 0.13544891774654388, 0.34829720
Computing hypergeometric distribution function for
P{X<=10} when n=m=30 and k=15
In [9]:
P_i = arr.array(’f’)
n = 30
m = 30
k = 15
i = min(k,n)
for x in range(i+1):
if x==0:
P_i.insert(x,combination(m,k)/combination(n+m,k))
else:
alpha = (n-x+1)/x
beta = (k-x+1)/(m-k+x)
P_i.insert(x,alpha*beta*P_i[x-1])
print("P{X = i} i from 0 to 15 values")
print(P_i)
value = 10
print("P{X <= 10}")
P_sum = 0
for x in range(value+1):

31
 P_sum = P_sum + P_i[x]
print(P_sum)
P{X = i} i from 0 to 15 values
array(’f’, [2.9160669328121003e-06, 8.201438322430477e-05, 0.0009
P{X <= 10}
0.9641908090575271
In [ ]:

32
 Aditi Rai
Question No.20
Independent trials, each of which is a success with
probability p, are successively performed. Let X
denote the first trial resulting in a success. That
is, X will equal k if the first k−1 trials are all fail-
ures and the kth a success. X is called a geometric
random variable. Compute
(a) P{X = k}, k = 1, 2, . . .;
(b) E[X].
Let Y denote the number of trials needed to
obtain r successes. Y is called a negative binomial
random variable. Compute
(c) P{Y = k}, k = r, r + 1, . . . .
(Hint: In order for Y to equal k, how many
successes must result in the first k−1
trials and what must be the outcome of trial
k?)
(d) Show that
E[Y ] = r/p
(Hint: Write Y = Y1 + . . . + Yr where Yi is
the number of trials needed to go
from a total of i ? 1 to a total of i successes.)
Solution :
1. Let X denote the first trial resulting in a success.
That is, X will equal k if the first k1 trials are all
failures and kth a success. The Probability of success
is p and probability of failure is 1-p. So,
P { X = k } = p (1-p)k−1 (ANS)

33
 2. E (X) = Σ k P (X = k)
= Σ k pP (1-p)k−1
k−1 k−1
P
= p ( k=1 (1 − p) + k=2 (1 − p) +
k−1
P
k=3 (1 − p) + ..................)
= p ( 1 / 1-(1-p) + (1-p) / 1-(1-p) + (1-p)2 / 1-(1-p)
+ . . . . . . . . . ..)
= ( p / 1-(1-p) + p(1-p) / 1-(1-p) + p(1-p)2 / 1-(1-p)
+ . . . . . . . . . ..)
= (1 + (1-p) + (1-p)2 + . . . . . . . . . . . . . . . .)
= 1/1 - (1-p)
= 1/p (ANS)
3. Let Y denote the number of trials needed to obtain
r successes.
P { Y = k } = k−1

r k−r
r−1 p (1-p) (ANS)
4. Let Y1 denote the number of trials before the 1st suc-
cess
Y2 =number of trials between the 1st and 2nd success
Yr = number of failures between the (r1)-th and r-th
success.
Since Y is the total number of trials
Y = Y1 + Y2 + . . . . . . . . . . . . . . . + Yr
Observe that Yi is a Geometric random variable for i
= 1,2,. . . . . . r and Yi ’s are independent events. So,
E ( Y ) = E ( Y1 ) + E ( Y2 ) + . . . . . . . . . . . . r times
= p1 + p1 + . . . . . . . r times
= pr (ANS)

34
 Ashish Bhatia
Question No.21
If U is uniformly distributed on (0, 1), show that
a+(b-a)U is uniform on (a, b)
Solution:
U is uniform distribution
Ry on(0,1).so, P(U < y) is
P (U ≤ Y ) = 0 f (U )du
P (a + (b − a)U ≤ x) = P (U ≤ x−ab−a )
Z x−a
b−a
= f (U )du
0

(x − a)
=
(b − a)

35
 Rishita Srivastava
Question No.22
You arrive at a bus stop at 10 o’clock, knowing that
the bus will arrive at some time uniformly distributed
between 10 and 10:30. What is the probability that you
will have to wait longer than 10 minutes? If at 10:15 the
bus has not yet arrived, what is the probability that you
will have to wait at least an additional 10 minutes?

Solution:
Given that bus arrives uniformly at the bus stop between
10 am and 10:30 am. Let X denote the arrival of bus
at the bus stop. Then X is a uniform random variable
having density as
1
f(x) = 30 ;x∈[0, 30]
1. Probability that a passenger arriving at the bus stop
between 10 and 10:30 will have to wait
10 more minutes.
R 30 R 30 1 1 30 1
P[x>10]= 10 f (x) dx= 10 30 dx= 30 [x]10 = 30 [30 − 10] = 23 = 0.67
1. At 10:15 Am, bus has not arrived. Probability that
the passenger will have to wait additional
10 minute is given as: R 301
30 dx
T
P [x>25 x>15] P [x>25]
P[x>25|x>15] = P [x>15] = P [x>15] = R25
30 1 =
15 30
dx
1
[30−25] 1
30
1
[30−15]
= 3
30

36
 Ashish Kumar Sharma
Question No.23

23. If X is a normal random variable with parameters µ

= 10, σ 2 = 36, compute:
(a) P{X > 5};
(b) P{4 < X < 16};
(c) P{X < 8};
(d) P{X < 20};
(e) P{X > 16}.

Solution: Given X is a normal random variable with

mean µ =10 and variance σ 2 = 36
To compute the following probabilities we will make use
of the fact that if X ∼ N(µ , σ 2 ), then Z = X−µ
σ ∼ N(0,1),
i.e; Z is a standard normal variable with φ being its CDF,
whose probability can be computed using the standard
normal table.
1.
h i
X−µ 5−10
P{X>5} = P σ > 6

= P Z > −5
 
6
 
−5
=1−φ
6
= 1 − 0.2023
= 0.7977

37
(b) h i
4−10 X−µ 16−10
P{4 < X < 16} = P 6 < σ < 6

= P [−1 < Z < 1]

= φ (1) − φ (−1)
= 0.8413 – 0.1586
= 0.6827
(C) h i
X−µ 8−10
P{X < 8} = P σ > 6

−1
 
=P Z< 3
 
−1
=φ
3
= 0.3694
(d) h i
X−µ 20−10
P{X < 20} = P σ > 6

5
 
=P Z< 3
 
5
=φ
3
= 0.9522

(e) h i
X−µ 16−10
P{X > 16} = P σ > 6

= P{Z<1}
= 1 − φ (1)

38
= 1 − 0.8413
= 0.1586

39
 Harendra Singh
Question No.24
Question 24 : The Scholastic Aptitude Test mathematics
test scores across the population of high school seniors
follow a normal distribution with mean 500 and standard
deviation 100. If five seniors are randomly chosen, find
the probability that (a) all scored below 600 and (b) ex-
actly three of them scored above 640.

Answer : X is Normal Random variable (test score) with

parameters
µ = 500 and σ = 100

(a) : Probability that all scored below 600 P(A)

P (A) = P (X < 600)5

= P (X − µ < 600 − µ)5

 5
X − µ 600 − µ
= P <
σ σ

 5
600 − 500
= P z<
100

 5
100
= P z<
100

40
 = P (z < 1)5

= (0.8413)5

= 0.4214
(b) : Probability that exactly three of them scored above
640(B).
P (B) = P (X < 640)2 P (X > 640)3

= P (X − µ < 640 − µ)2 P (X − µ > 640 − µ)

 2  3
X − µ 640 − µ X −µ X −µ
= P < P >
σ σ σ σ

 2  3
640 − 500 640 − 500
= P z< P z>
100 100

= P (z < 1.4)2 P (z > 1.4)3

P (z < 1.4)2 (1 − P (z < 1.4))2

41
= (0.9192)2 (1 − 0.9192)2

= 0.845 × 0.0065 = 0.0055

42
 Prakhar Agrawal
Question No.25
The annual rainfall (in inches) in a certain region is nor-
mally distributed with = 40, = 4. What is the proba-
bility that in 2 of the next 4 years the rainfall will exceed
50 inches? Assume that the rainfalls in different years
are independent.

Solution:

X is a normal random variable(annual rainfall)with parameter, µ =

40 and σ = 4.

Probability that in 2 of the next 4 years the rainfall

will exceed 50 inch P(A)
P(A) = 42 c P [x ≤ 50]2 P [x > 50]2
= 42 cP [x − µ ≤ 50 − µ]2 P [x − µ > 50 − µ]2
x−µ 50 − µ 2 x − µ 50 − µ 2
= 42 cP [ ≤ ] P[ > ]
σ σ σ σ
4 50 − 40 2 50 − 40 2
= 2 cP [z ≤ ] P [z > ]
10 10
= 42 cP [z ≤ 1.25]2 P [z > 1.25]2

= 6 x 0.89442 (1 − 0.8944)2 = 6 x 0.8 x 0.0111 = 0.05328

43
 Akshay Kumar
Question No.26
Q.26
The width of a slot of a duralumin forging is (in inches)
normally distributed with µ = .9000 and σ = .0030. The
specification limits were given as .9000±.0050. What
percentage of forgings will be defective? What is the
maximum allowable value of that will permit no more
than 1 in 100 defectives when the widths are normally
distributed with µ = .9000 and σ = .0030

SOLUTION:- Given that the width of the duralumin

forging(in inches) is normally distributed with mean y =
0.9000 and standard deviation σ = 0.0030. The specifi-
cation limits mentioned are 0.9000 + 0.0050 and 0.9000
- 0.0050.

(a) To determine what percentage of forgings will be

defective, we first calculate the probability of the num-
ber of defectives within the specified limits
P[0.9000 – 0.0050 < X < 0.9000 + 0.0050] = P(0.895 <
X < 0.9050]

0.895−0.9000 X−µ 0.9050−0.9000

P[ 0.0030 < σ < 0.0030 ]

−0.0050 0.0050
P[ 0.0030 <Z< 0.0030 ]

=P[-1.666 < Z < 1.666]

44
=2 [0 < z < 1.666]

=2 ×[Φ(1.67) − 0.5]

= 2 × (0.9525 − 0.5)

=0.9050

45
 Probability of number of defectives within the speci-
fied range is

1 - 0.9050 = 0.0950

Hence, 9.5 Probability of number of defectives within

the specified range is

1 -0.9050 = 0.0950

Hence, 9.5 percent of forgings will be defective.

46
 2nd part Ans:
determine the value of σf orwhichtherewillbenomorethan1in100def ectivef org
P[0.9000 – 0.0050 < X < 0.9000 + 0.0050] = 0.99

P(0.895 < X < 0.9050) = 0.99

0.895−0.9000 X−µ 0.9050−0.9000

P[ σ < σ < σ ] = 0.99

P[ −0.005
σ <Z< 0.005
σ ] = 0.99

0.005
2 [0 < Z < σ ] = 0.99

2 ×[Φ( 0.005
σ )- 0.5] = 0.99

Φ( 0.005
σ )= 0.995
σ = 0.0019

comment : useZtable

47
 Kaveti Pavan
Question No.27
27.) A certain type of light bulb has an output that is
normally distributed with mean 2,000 end foot candles
and standard deviation 85 end foot candles. Determine
a lower specification limit L so that only 5 percent of the
light bulbs produced will be defective. (That is, deter-
mine L so that PX L = .95, where X is the output of a
bulb.)

solution:

Mean of the normal distribution is µ = 2000

and the standard deviation is σ = 85
Let X be the random variable.
N ow,
X −µ
Z=
σ
X1 − 2000
and Z1 =
85
95 percent of the observation lie above X1
P (z > z1 ) = 0.95
P (z < z1 ) = 0.05
−z1 = 1.64
N ow,
X1 − 2000
z1 =
85

48
 X1 − 2000
−1.64 =
85
X1 − 2000 = −139.4
X1 = 2000 − 139.4
X1 = 1860.6

49
 Umar Abdullah
Question No.28
Question: A manufacturer produces bolts that are spec-
ified to be between 1.19 and 1.21 inches in diameter. If
its production process results in a bolt’s diameter being
normally distributed with mean 1.20 inches and stan-
dard deviation .005, what percentage of bolts will not
meet specifications?
Solution:
X is a normal random variable with parameters µ = 1.20
and σ = 0.005
Probability that bolt will not meet specifications
i.e. P (X < 1.19)orP (X > 1.21)
P (X < 1.19) ∪ P (X > 1.21) = P (X − µ < 1.19 − µ) +
P (X − µ > 1.21 − µ)
= P ( X−µ
σ <
1.19−µ X−µ
σ ) + P( σ >
1.21−µ
σ )
1.19−1.20 1.21−1.20
= P (Z < 0.005 ) + P (Z > 0.005 )
0.01 0.01
= P (Z < − 0.005 ) + P (Z > 0.005 )
= P (Z < −2) + P (Z > 2)
= 2 ∗ P (Z > 2)
= 2 ∗ (1 − P (Z < 2))
= 2 ∗ (1 − 0.9772)
= 0.0456

50
 Amit Kumar Behera
Question No.29

Not understood

51
 Sambodhi Sengupta
Question No.30

Not understood

52
 Medha Misra
Question No.31
The lifetimes of interactive computer chips pro-
duced by a certain semiconductor manufacturer
are normally distributed having mean 4.4 × 106 hourswith
a standard deviation of 3 × 105 hours. If a main-
frame manufacturer requires thatat least 90 per-
cent of the chips from a large batch will have life-
times of at least 4.0 × 106 hours, should he con-
tract with the semiconductor firm?

Answer 31.
Given,
The value of µ= 4.4 × 106 hours and σ = 3 ×
105 hours
Let’s suppose that the lifetime of the chips is
denoted by ’T’
Now, we have,
P(T >= 4.106 ) = 1 - P(T <=4.106 )
6
−4.4×106
P(T >= 4.106 ) = 1 - ϕ ( 4×10 3.10 5 )
6 4
P(T >= 4.10 ) = 1 - ϕ (− 3 )
P(T >= 4.106 ) = ϕ ( 34 )
P(T >=4.106 ) ≈ 90.1%
Thus, he should sign the contract with the firm
Result - Yes, he should contract with the semi-
conductor firm.

53
 Asif Raza
Question No.32
In Problem 31, what is the probability that a batch of
100 chips will contain at least 4 whose lifetimes are less
than 3.8 × 106 hours?

Solution:

µ = 4.4 ∗ 106
Standard Deviation = σ 2 = 3 ∗ 106
x = 3.8 * 106
x−µ
Z=
S.D
(3.8 − 4.4) ∗ 106
Z=
3 ∗ 105
−0.6 ∗ 10
Z= = −2
3
φ(−2) = 0.02275
P ≈ 0.0228
Probability that a batch of 100 chips will contain at
least 4 whose lifetimes are less than 3.8×106 hours.

P(X≥ 4) = 1 − P (X = 0) − P (X = 1) − P (X =
2) − P (X = 3)

n = 100, P = 0.0228
n! n!
⇒ P (X ≥ 4) = 1−[ 0!(n−0)! ∗P 0 ∗(1−P )n−0 ]−[ 1!(n−1)! ∗
n! n!
P 1 ∗ (1 − P )n−1 ] − [ 2!(n−2)! ∗ P 2 ∗ (1 − P )n−2 ] − [ 3!(n−3)! ∗

54
P 3 ∗ (1 − P )n−3 ]
100!
⇒ P (X ≥ 4) = 1−[ 0!(100−0)! ∗0.02280 ∗(1−0.0228)100−0 ]−
100! 100!
[ 1!(n−1)! ∗ 0.02281 ∗ (1 − 0.0228)100−1 ] − [ 2!(100−2)! ∗ 0.02282 ∗
100!
(1−0.0228)100−2 ]−[ 3!(100−3)! ∗0.02283 ∗(1−0.0228)100−3 ] ⇒

P (X ≥ 4) = 1 − [0.0997 + 0.2324 + 0.2684 + 0.2046] ⇒

P (X ≥ 4) = 1 − 0.8051 ⇒ P (X ≥ 4) = 0.195

Probability that a batch of 100 chips will contain at

least 4 whose lifetimes are less than 3.8×106 hoursisequalto0.195

55
 Inzamam Safi
Question No.33
Question: . The lifetime of a color television picture
tube is a normal random variable with mean 8.2 years
and standard deviation 1.4 years. What percentage of
such tubes lasts.
(a) more than 10 years;
(b) less than 5 years;
(c) between 5 and 10 years?
Solution:

(a)
p(x>10)=1-p(x<10)
z=(10-8.2)/1.4
=1.285
checking probability value using z table
=0.899
p(x>10)=1-0.899
=0.10027
——
(b)
p(x<5)
z=(5-8.2)/1.4
=-2.285
checking probability value using z table
=0.01130
p(x<5)=0.01130
——
(C)
p(5<x<10)=p(x<10)-p(x<5)

56
p(x<10)=0.899(using Q(a))
p(x<5)= 0.01130(using Q(b))
p(5<x<10)= 0.899-0.01130
=0.8877

57
 Arjit Kumar
Question No.34
QUESTION 34 -The annual rainfall in Cincinnati is nor-
mally distributed with mean 40.14 inches and standard
deviation 8.7 inches.
(a) What is the probability this year’s rainfall will
exceed 42 inches?
(b) What is the probability that the sum of the next
2 year’s rainfall will exceed 84 inches?
(c) What is the probability that the sum of the next
3 year’s rainfall will exceed 126 inches?
(d) For parts (b) and (c),what independence assump-
tions are you making?
SOLUTION 34- It is given that the annual rainfall
in Cincinnati is normally distributed with mean 40.14
inches and standard deviation 8.7 inches.
(a) Here, we have to find the probability that this
year’s rainfall (say X) will exceed 42 inches, that is,

42−mean
P(X > 42) = P(z > standarddeviation )

42−40.14
= P(Z > 8.7 )

1.86
= P(Z > 8.7 )

= 1 − Φ(0.21)

= 1 - 0.5846

= 0.4154

58
Thus, we found that the probability that this year’s rain-
fall will exceed 12 inches is 0.4154

(b) Here, we have to find the probability that the sum of

the next two year’s rainfall (say X1 and X2) will exceed
84 inches. Since X1 follows mean 40.14 and standard
deviation 8.7 and X2 follows mean 40.14 and standard
deviation 8.7. Thus, Y = X1 + X2 follows √mean 40.14+
40.14
√ = 80.28 √and standard deviation = 8.72 + 8.72 =
28.72 = 8.7( 2).
Therefore, we found that,

84−mean
P(Y > 84) = P(z > standarddeviation )

84−80.28
= P(Z > 8.72 )

= 1 - Φ( 3.72
8.72 )

= 1- 0.6188

= 0.3812
Thus, we found that the probability that the sum of the
next two years rainfall will exceed is 0.3812.

(c) Here, we have to find the probability that the sum of

the next three year’s rainfall (say X1, X2 and X3) will
exceed 126 inches. Since X, follows mean 40.14 and stan-
dard deviation 8.7, X2 follows mean 40.14 and standard
deviation 8.7, and X3 also follows mean 40.14 and stan-
dard deviation 8.7.
Thus, Y = X1 + X2 + X3 follows mean 40.14 + 40.14 +

59
 √
40.14
√ = 120.42 and
√ standard deviation 8.72 + 8.72 + 8.72
= 8.72 ∗ 3 =8.7( 3) = 15.0684.
Therefore
126−mean
P(Y > 126) = P(z > standarddeviation )

126−120.42
= P(Z > standarddeviation )

5.58
= P(Z > standarddeviation )

5.58
= 1- Φ( 15.0684 )

= 0.356 Thus, we found that the probability that the

sum of the next three year’s rainfall will exceed 126
inches is 0.356.
(d) In part (b) of this problem, we found that the
probability that the sum of the next two year’s rainfall
will exceed 84 inches is 0.3811 and in part (c), we found
that the probability that the sum of the next three year’s
rainfall will exceed 126 inches is 0.356.
For both the parts, the probability was found on the
basis of normal distribution of data of rainfall. Also, it
can be observed that the probability in both the parts
is less than 50%, therefore, the probability is an unlikely
event. But, the probability that the sum of the next
two Year’s rainfall will exceed 81 inches is more than the
probability that the sum of the next three years rainfall
will exceed 126 inches.

60
 Md Ahmad Jami
Question No.35
QUESTION 35
The height of adult women in the United States is
normally distributed with mean 64.5 inches and stan-
dard deviation 2.4 inches. Find the probability that a
randomly chosen woman is
(a) less than 63 inches tall;
(b) less than 70 inches tall;
(c) between 63 and 70 inches tall.
(d) Alice is 72 inches tall. What percentage of women
is shorter than Alice?
(e) Find the probability that the average of the heights
of two randomly chosen women exceeds 66 inches.
(f ) Repeat part (e) for four randomly chosen women.

SOLUTION - It is given that the height of adult women

in the United States is normally distributed with mean
64.5 inches and a standard deviation 2.4 inches.
(a) Here, we have to find the probability that a ran-
domly chosen women (say X) is less than 63 inches tall,
that is,
63−mean
P(X < 63) = P(z < standarddeviation )
63−64.5
= P(Z< 2.4 )

= Φ(−1.5/2.4)

= Φ(−0.625)

= 1- Φ(0.625)

61
 = 1-0.734

= 0.266
(b) Here, we have to find the probability that a ran-
domly chosen women (say X) is less than 70 inches tall,
that is,
70−mean
P(X < 70) = P(z < standarddeviation )
70−64.5
= P(Z< 2.4 )

= Φ(5.5 2.4 )

= Φ(2.292)

= 0.989
(c) Here, we have to find the probability that a ran-
domly chosen women (say X) is between 63 and 70 inches
tall, that is,
P(63 < X < 70) = P(X < 70)- P(X < 63)
= 0.989- 0.266
= 0.723
(d) It is given that Alice is 72inches tall. We have
to find what percentage of women is shorter than Alice
which will be 100 times the probability of women less
than 72 inches. Thus, we found that,
P(X < 72)
72−mean
= P ( Z< standarddeviation )

72−64.5
= P(z < 2.4 )

62
 = Φ(7.5 2.4 )

= Φ(3.125)
= 0.999
The percentage of women is shorter than Alice is 0.999
x 100 = 99.9%.
(e) Here, we have to find the probability that the av-
erage of the heights of two randomly chosen women (say
X1 and X2) exceeds 66 inches. Here, the average for two
is 66, therefore, in total it is 2x66 =132 inches. Since
X1 follows mean 64.5 and standard deviation 2.4 and X2
follows mean 64.5 and standard deviation 2.4. Thus, Y
= X1 + X2, √ follows mean 64.5+64.5=
√ 129 and standard
deviation = 2.42 + 2.42 = 22.42 =2.42.
Therefore, we found that
P(Y > 132)
132−mean
= P(z > standarddeviation )

= P(Z > 132−129

2.42 )

3
= P(Z > 2.42 )

= 1-0.812
= 0.188
(f) Here, we have to find the probability that the av-
erage of the heights of two randomly chosen women (say
X1, X2, X3 and X4) exceeds 66 inches. Here, the aver-
age for four is 66, therefore, in total it is 4 x 66 = 264
inches. Since each X1, X2, X3 and X4 follows mean 64.5
and standard deviation 2.4.

63
 Thus, Y = X1+X2+ X3+X4√ follows mean 64.5+64.5+64.5+64.5
= 258 2 2 2 2
√ and standard deviation 2.4 + 2.4 + 2.4 + 2.4
= 2.42 ∗ 4 = 2.4 x 2= 4.8. Therefore, we found that,
P(Y > 264)
264−mean
= P(z > standarddeviation )

262−258
= P(z > 4.8 )

6
= P(z > 4.8 )

= 1-Φ(6 4.8 )

= 1 - 0.894

= 0.106

64
 Uditanshu Gupta
Question No.36
An IQ test produces scores that are normally dis-
tributed with mean value 100 and standard devi-
ation 14.2. The top 1 percent of all scores is in
what range?

Solution:-
An IQ test produces scores that are normally distributed
with the mean value 100 and standard deviation 14.2.
We have to find the range in which the top 1 percent of
all score lies.
Thus we have to find the value of x such that:

Φ(0.01) = (x − mean)/ standard deviation

Φ(0.01) = (x–100)/14.2
Multiply 14.2 on both the sides we get,
Φ(0.01)∗ 14.2 = (x – 100)
Adding 100 on both sides we get,
Φ(0.01)∗ 14.2 + 100 = x – 100 + 100
Φ(0.01) ∗ 14.2 + 100 = x { put value Φ(0.01) = 2.58 }
2.58 ∗ 14.2 + 100 = x
136.636 = x
Value of x will be approx: 136.64
Thus, we found that the top 1 percent of all scores lies
below 136.64 approximately.

65
 Uditanshu Gupta
Question No.37
The time (in hours) required to repair a machine is an
exponentially distributed Random variable with param-
eter λ = 1/2.

(a) What is the probability that a repair time exceeds

2 hours?
(b) What is the conditional probability that a repair
takes at least 3 hours, given that its duration exceeds 2
hours?

Solution:-

Let T denote the time (in hours) required to repair the

machine. Given that T ∼ Exp (λ = 1). Thus we have

n
e−t
fT (t) = 2 t¿0
1. otherwise

Now,

1. Probability that repair time exceeds two hours is,

R ∞ e−t
P [T > 2] = 2 2 dt

66
 h 2
i
1 −t
P [T > 2] = 2 e ∗ t2
By putting upper limit and lower limit we get

1 −2


P [T > 2] = ∗ −4 e4

−2


P [T > 2] = − e will be the an-
swer.

2. Probability that repair time will exceed 10 hours

given that it has exceeded 9 hours is given as P [T
> 10 | T > 9]. Here, we make use of the memory
less property of the exponential distribution, which
states that for (t¡s)

P [T > s | T > t] = P [T > s-t]

Thus we have,

P [T ¿ 10 | T > 9] = P [T > 10-9]

67
P [T > 10 | T > 9] = P [T > 1]
R ∞ e−t
P [T > 10 | T > 9] = 1 2 dt

P [T > 10 | T > 9] = 41 ∗ − e−1

−(e−1 )
P [T > 10 | T > 9] = 4 will be the
answer.

68
 Uditanshu Gupta
Question No.38

The number of years a radio functions is expo-

nentially distributed with parameter λ = 1/8. If
Jones buys a used radio, what is the probability
that it will be working. After an additional 10
years?
Solution:-

Let X is the number of years a radio function. We do

not know the age of john’s second hand radio but it is
given that it is still functioning, we can assume its age is
the expected value of X, which is given as,

E[X] = λ1 = 1/8
1

E[X] = 8

Hence, the conditional probability that Jones’s radio func-

tions for another 10 years would be given by,

P {X≥20|X≥10}
P{ X≥ 20 | X≥ 10 } = P {X≥10}

Off course, P{ X≥ 20 | X≥ 10 } = P {X ≥ 20 } ,
−1
P {X>=20} e 8 ∗20
Thus P{ X≥ 20 | X≥ 10 } = P {X>=10} = −1∗10
e 8
P{ X≥ 20 | X≥ 10 } = e−1.25 will be the Answer.

69
 Ashish Bhatia
Question No.39

Jones figures that the total number of thou-

sands of miles that a used auto can be driven
before it would need to be junked is an expo-
nential random variable with parameter 1/20 .
Smith has a used car that he claims has been
driven only 10,000 miles. If Jones purchases the
car, what is the probability that she would get
at least 20,000 additional miles out of it? Repeat
under the assumption that the lifetime mileage
of the car is not exponentially distributed but
rather is (in thousands of miles) uniformly dis-
tributed over (0, 40).
Solution:

Let X be the number of miles that car can driven be-

fore being junked
let X ∼ Exp(1/20)
We know that the car has driven 10,000 mile and we
want to find the probability that it will last an addi-
tional 20,000 miles .We use the memory less property of
exponential distribution where t=10,000 and s= 20,000
P(X≥ 10000+20000|X≥10000)=P(X≥ 20000)
P (X≥ 30000|X≥10000)=P(X<20000)
R ∞ −1
= 20 e 20 x dx
= e−1
We now have that X ∼ U N IF (0, 40) and wish to calcu-
late the conditional probability

70
P (X ≥ 30|X ≥ 10) R 401 40−30
P (X≥30∩X≥10) P (X≥30) 40 dx 10
= P (X≥10) = P (X≥10) = R30
40 1 = 40
40−10 = 30 = 13 .
10 40
dx 40

71
 Question No.42

Not understood

72
 Question No.43

Not understood

73
 Question No.44

Not understood

74
 Question No.45

Not understood

75
 Question No.46

Not understood

76
 Question No.48

Not understood

77