Math 365: Elementary Statistics

Homework and Problems (Solutions)

Satya Mandal

Spring 2019, Updated Spring 22, 6 March

2
Contents

1 The Language and Terminology 5

1.1 The Language and Terminology . . . . . . . . . . . . . . . . . 5

2 Measures of Central Tendency

and Measures of Dispersion 7
2.1 Mean and Median . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.2 Variance and Standard Deviations . . . . . . . . . . . . . . . . 9

3 Probability 13
3.1 Basic Concept of Probability . . . . . . . . . . . . . . . . . . . 13
3.2 Probability Table and Equally likely . . . . . . . . . . . . . . 13
3.3 Laws of Probability . . . . . . . . . . . . . . . . . . . . . . . . 15
3.4 Counting Techniques and Probability . . . . . . . . . . . . . . 16
3.5 Conditional Probability and Independence . . . . . . . . . . . 18

4 Random Variables 23
4.1 Random Variables . . . . . . . . . . . . . . . . . . . . . . . . . 23
4.2 Probability Distribution . . . . . . . . . . . . . . . . . . . . . 23
4.3 The Bernoulli and Binomial Experiments . . . . . . . . . . . . 26

3
4 CONTENTS

5 Continuous Random Variables 29

5.1 Probability Density Function (pdf) . . . . . . . . . . . . . . . 29
5.2 The Normal Random Variable . . . . . . . . . . . . . . . . . . 29
5.2.1 Inverse Normal . . . . . . . . . . . . . . . . . . . . . . 31
5.3 Normal Approximation to Binomial . . . . . . . . . . . . . . . 35

6 Elements of Sampling Distribution 39

6.1 Sampling Distribution . . . . . . . . . . . . . . . . . . . . . . 39
6.2 Central Limit Theorem . . . . . . . . . . . . . . . . . . . . . . 39
6.3 Distribution of the Sample Proportion . . . . . . . . . . . . . 42

7 Estimation 45
7.1 Point and Interval Estimation . . . . . . . . . . . . . . . . . . 45
7.1.1 Confidence Interval of µ . . . . . . . . . . . . . . . . . 45
7.1.2 The Required Sample Size . . . . . . . . . . . . . . . . 47
7.2 Confidence interval for µ when σ is unknown . . . . . . . . . . 48
7.3 About the Population Proportion . . . . . . . . . . . . . . . . 50
7.4 Confidence Interval of the Variance σ 2 . . . . . . . . . . . . . 51

8 Comparing Two Populations 53

8.1 Confidence Interval of µ1 − µ2 . . . . . . . . . . . . . . . . . . 53
8.2 When σ1 and σ2 are unknown . . . . . . . . . . . . . . . . . . 55
8.3 Comparing Two Population Proportions . . . . . . . . . . . . 56

9 Testing Hypotheses 59
9.1 A Significance Test for mean µ when σ is known . . . . . . . . 59
9.2 A Significance Test for mean µ when σ is unknown . . . . . . 61
9.3 Population Proportion . . . . . . . . . . . . . . . . . . . . . . 64
9.4 Testing Hypotheses on Variance σ 2 . . . . . . . . . . . . . . . 66
Chapter 1

The Language and Terminology

1.1 The Language and Terminology

1. Consider the following is data on the 9-month salary of mathematics
faculty members (to the nearest thousand dollars) in the year 1999-00:

61 63 72 80 70 76 97 60 57 65
67 73 66 75 61 54 61 65 70 68
(1.1)
53 50 50 40 51 44 62 57 51 52
50 57 52 52 56 46

Use class width = 10K. Complete the following frequency table:

Class 39.5 − 49.5 49.5 − 59.5 59.5 − 69.5 69.5 − 79.5 79.5 − 89.5 89.5 − 99.5
F req

2. Following is the grand total (out of 400) of scores obtained by students

in a class.
386 343 287 394 303 280 333 389 376 350
388 380 320 391 371 354 366 354 284 298
327 386 380 370 363 382 362 384 343 352 (1.2)
350 391 345 385 310 380 381 362 326 82
391 328 345 376

5
6 CHAPTER 1. THE LANGUAGE AND TERMINOLOGY

We use class width = 50. Complete the frequency table of the date
data in (1.2):
Class F requency
51 − 100
101 − 150
151 − 200
201 − 250
251 − 300
301 − 350
351 − 400
If a data value falls on the boundary, count it on the left interval.

3. The following is data on the weight (in ounces), at birth, of some babies.

74 105 124 110 119 137 96 110 120 115 140

65 135 123 129 72 121 117 96 107 80 91
74 123 124 124 134 78 138 106 130 97 145
93 133 128 96 126 124 125 127 62 127 92
95 118 126 94 127 121 117 124 93 135 156 (1.3)
143 125 120 147 138 72 119 89 81 113 91
133 127 138 122 110 113 100 115 110 135 141
97 127 120 110 107 111 126 132 120 108 148
143 103 92 124 150 86 121 98 74 85 99

Complete the frequency table of the weight distribution data in (1.3):

Class F requency
60.5 − 70.5
[70.5 − 80.5
80.5 − 90.5
90.5 − 100.5
100.5 − 110.5
110.5 − 120.5
120.5 − 130.5
130.5 − 140.5
140.5 − 150.5
150.5 − 160.5
Chapter 2

Measures of Central Tendency

and Measures of Dispersion

2.1 Mean and Median

1. The following is the price (in dollars) of a stock (say, CISCO SYS-
TEMS) checked by a trader several times on a particular day.

139 143 128 138 149 131 143 133

(a) Find the mean price (in dollars) observed by the trader.
(b) Find the median price observed by the trader (in dollars).

2. The following figures refer to the GPA of six students:

3.0 3.3 3.1 3.0 3.1 3.1

(a) Find the median of the GPA.

(b) Find the mean of the GPA.

3. The following data give the lifetime (in days) of certain light bulbs.

138 952 980 967 992 197 215 157

7
8CHAPTER 2. MEASURES OF CENTRAL TENDENCYAND MEASURES OF DISPERSIO

(a) Find the mean for the lifetime of these light bulbs.
(b) Find the median for the lifetime of the bulbs.

4. An athlete ran an event 32 times. The following frequency table gives

the time taken (in seconds) by the athlete to complete the events.

Time (in seconds) Frequency

11.6 4
11.7 5
11.8 6
11.9 7
12.0 6
12.1 4
Total 32

(a) Compute the mean time taken by the athlete. (Write up to 4

significant digits.)
(b) Find the median time taken by the athlete

5. The following are the weights (in ounces), at birth, of 30 babies born
in Lawrence Memorial Hospital in May 2000.
94 105 124 110 119 137 96 110 120 115
104 135 123 129 72 121 117 96 107 80
96 123 124 124 134 78 138 106 130 97

(a) Compute the mean weight, at birth, of the babies.

(b) Using the previous table, compute the median weight, at birth, of
the babies.

6. Following is a frequency table for the hourly wages (paid only in whole
dollars) of 99 employees in an industry.

Hourly Wages 7 8 9 10 11 12 13 14 15 16 17 18 19
Frequency 1 4 10 4 9 8 6 5 17 19 3 1 2

(a) Compute the mean hourly wage.

(b) Using the previous frequency table, compute the median hourly
wage.
2.2. VARIANCE AND STANDARD DEVIATIONS 9

7. The following is the frequency table on the number of typos found in

a sample of 30 books published by a publisher.

Number of Typos 156 158 159 160 162

Frequency 6 4 5 6 9

(a) Compute the mean number of typos in a book.

(b) Using the previous frequency table, compute the median number
of typos found in a book.

8. The following are the lengths (in inches), at birth, of 14 babies born in
Lawrence Memorial Hospital in May 2000.

Length 17 18.5 19 20 21.5

Frequency 2 3 4 3 2

(a) Compute the mean length, at birth, of these babies.

(b) Using the previous table, compute the median length, at birth, of
these babies.

2.2 Variance and Standard Deviations

1. The following is the price (in dollars) of a stock (say, CISCO SYS-
TEMS) checked by a trader several times on a particular day.

138 142 127 137 148 130 142 133

(a) Find the variance of the price (to four decimal places).
(b) Find the standard deviation of the price (to four decimal places).

2. The following figures refer to the GPA of six students:

3.0 3.3 3.1 3.0 3.1 3.1

(a) Find the variance of the GPA (to four decimal places).
(b) Find the standard deviation of the GPA (to four decimal places).
10CHAPTER 2. MEASURES OF CENTRAL TENDENCYAND MEASURES OF DISPERSI

3. The following data give the life time (in days) of certain light bulbs.
938 952 980 967 992 997 915 957
(a) Find the variance for the life time of these bulbs (to four decimal
places).
(b) Find the standard deviation for these bulbs (to four decimal places).
4. An athlete ran an event 32 times. The following frequency table gives
the time taken (in seconds) by the athlete to complete the events.
Time (in seconds) Frequency
11.6 4
11.7 5
11.8 6
11.9 7
12.0 6
12.1 4
Total 32
(a) Compute the variance for the times taken by the athlete (to four
decimal places).
(b) Find the standard deviation for the times taken by the athlete (to
four decimal places).
5. The following are the weights (in ounces), at birth, of 30 babies born
in Lawrence Memorial Hospital in May 2000.
94 105 124 110 119 137 96 110 120 115
104 135 123 129 72 121 117 96 107 80
96 123 124 124 134 78 138 106 130 97
(a) Compute the variance of the weight, at birth, of the babies.
(b) Compute the standard deviation of the weight, at birth, of the
babies.
6. Following is a frequency table for the hourly wages (paid only in whole
dollars) of 99 employees in an industry.
Hourly Wages 7 8 9 10 11 12 13 14 15 16 17 18 19
Frequency 11 4 10 4 9 8 6 5 17 19 3 1 2
2.2. VARIANCE AND STANDARD DEVIATIONS 11

(a) Compute the variance of the hourly wage.

(b) Compute the standard deviation of the hourly wage.

7. The following is a frequency table on the number of typos found in a

sample of 30 books published by a publisher.

Number of Typos 156 158 159 160 162

Frequency 6 4 5 6 9

(a) Compute the variance of the number of typos in a book.

(b) Compute the standard deviation of the number of typos in a book.

8. The following are the lengths (in inches), at birth, of 14 babies born in
Lawrence Memorial Hospital in May 2000.

Length 17 18.5 19 20 21.5

Frequency 2 3 4 3 2

(a) Compute the variance of the length, at birth, of these babies.

(b) Compute the standard deviation of the length, at birth, of these
babies.
12CHAPTER 2. MEASURES OF CENTRAL TENDENCYAND MEASURES OF DISPERSI
Chapter 3

Probability

3.1 Basic Concept of Probability

None

3.2 Probability Table and Equally likely

1. The following table gives the probability distribution of a loaded die.
Face 1 2 3 4 5 6
Probability 0.20 0.15 0.15 0.10 0.05 0.35
Find the probability that an even number face will show up when you
roll the die.

Solution:
P ({2, 4, 6}) = .15 + .10 + .35 = .60

2. A die is rolled twice. What is the probability that the two numbers are
unequal?

Solution: n(S) = 36
Let E =that the two numbers are unequal

13
14 CHAPTER 3. PROBABILITY

So, (not E) = (1, 1, ), (2, 2), (3, 3), (4, 4), (5, 5), (6, 6)
So, n(not E) = 6
So, n(E) = n(S) − n(notE) = 36 − 6 = 30
P (E) = n(E)
n(S)
= 30
36
= .8333

3. A student wants to pick a school based on the recent grade distribution

of the school. Following is the grade distribution of the previous year
in a school:

Grades A B C D F
Percentage of Students 19 33 31 14 3

What is the probability that a student will receive a C-grade or higher

in this school?

Solution: Let E = {C, B, A} =event that the selected student will

have a C-grade or higher
P (E) = .19 + .33 + .31 = .83

4. A container has 11 red balls, 15 green balls, 10 white balls, and 8 yellow
balls. A child picks up a ball from the container. Find the probability
that the ball is red.

Solution: Let E = {Red} =event that boy will pick up a red ball.
P (E) = n(E)
n(S)
= 11
33
= .3235

5. A die is rolled twice. What is the probability that the product of the
two numbers is 11?

Solution: Answer = 0

6. A magician asks you to pick a card from a deck of 52 cards. What is

the probability that you will pick a heart?
13
Solution: Answer = 52
= .25

7. You toss a coin 4 times. What is the total number of outcomes?

Solution: Answer = 24 = 16
3.3. LAWS OF PROBABILITY 15

8. The sex of 4 unborn children is to be determined in a lab today. What

is the probability that there will be at least 2 girls?

Solution: n(S) = 24 = 16
Let E = be the even that there would be at least two girls
(not E) = means 0 or 1 girl
So, (not E) = {BBBB, GBBB, BGBB, BBGB, BBBG}
n(not E) = 5
n(E) = n(S) − n(not E)=16-5=11
So, P (E) = n(E)
n(S)
= 11/16

3.3 Laws of Probability

1. Suppose E and F are two events. It is given that P(E)=.22, P(not
F)=.65, and P(E and F)=.13. Determine the probability that either E
or F occur.

Solution: First, P (F ) = 1 − P (not F ) = 1 − .65 = .35

P (E or F ) = P (E) + P (F ) − P (E and F ) = .22 + .35 − .13 = .44

2. Suppose E and F are two events. It is given that P(not E)=.33, P(not
F)=.54, and P(E or F)=.68. Determine the probability that both E
and F occur.

3. Use the information in Question 2. Determine the probability that

neither E nor F occur.

4. The proportion of students who own a vehicle is 0.55, and the propor-
tion of students who live in a dorm is 0.41. If the proportion of students
who either own a vehicle or live in a dorm is 0.83, find the proportion
of students who live in a dorm and own a vehicle.

5. The probability that it does not rain in Arizona in June is 0.22. Find
the probability that it rains at least once in the month of June in
Arizona.
16 CHAPTER 3. PROBABILITY

Solution: Let E = event that it rains at least once in June.

(not E) = event that it does not does not rain in June
P (not E) = .22
P (E) = 1 − P (not E) = 1 − .22 = .78

6. The probabilities that a particular office phone rings 0, 1, 2, 3 times in

half hour are respectively: .05, .15, .21, .42. Find the probability that
the phone rings at least 4 times between 3:30-4:00 pm.

Solution: E =event that it rings at least 4 times.

So, (not E) = {0.1, 2, 3}.
P (not E) = P (0, 1, , 2, 3) = P (0) + P (1) + P (2) + P (3) = .05 + .15 +
.21 + .42 = .83.
So, P (E) = 1 − P (not E) = 1 − .83 = .17.

7. The probability of a student going to a bar on Wednesday is 3/5. The

probability of the student going to class on Thursday is 4/5. If the
probability that the student either goes to the bar or goes to class the
next day is 9/10, what is the probability that the student will do the
both?

8. The probability that a student will major in mathematics is .13 and

the probability that a student will have a major in engineering is .31.
The probability that a student will double major in mathematics and
engineering is .07. What is the probability that a student will major
in mathematics or engineering?

3.4 Counting Techniques and Probability

1. Compute 8 C2 .

2. Suppose 2 scholarships, $1000 each, is to be given to 2 students. There

are 9 applicants. How many choices of 2 awardees are possible?

Solution: Each scholarship is worth same amount.

So, order of selection does not count.
It is an unordered selection.
3.4. COUNTING TECHNIQUES AND PROBABILITY 17

So, answer=9 C2 = n!/[(n − r)!r!] = 9!/[7!2!] = 9 ∗ 8/[1 ∗ 2] = 36.

3. Suppose 2 scholarships, one for $2000 and another for $1000, will be
given to 2 students. There are 9 applicants. How many choices of 2
awardees are possible?

Solution: Scholarships have distinct values.

So, order of selection has to be taken into account.
So, Answer=9 P2 = n!/(n − r)! = 9!/7! = 8 ∗ 9 = 72.

4. In an annual sports meet, 9 students compete in 2 events (the 100 meter

and 1000 meter race). How many ways can two winners can be picked?

Solution: Repetitions are allowed here.

Use multiplication principle:
First event : 9 choice
2nd event : 9 choice
Answer= product = 9 ∗ 9 = 81

5. A coin is tossed 6 times. What is the total number of possible out-

comes?

Solution: answer=2 ∗ 2 ∗ 2 ∗ 2 ∗ 2 ∗ 2 = 64

6. The sex of 8 unborn children is to be determined today in a lab. What

is the probability that 2 particular children (say the child of Elizabeth
and the child of Maria) will be boys?

Solution: Each child could be B or G.

n(S) = 2 ∗ 2 ∗ 2 ∗ 2 ∗ 2 ∗ 2 ∗ 2 ∗ 2 = 28
n(E) = 1 ∗ 1 ∗ 2 ∗ 2 ∗ 2 ∗ 2 ∗ 2 ∗ 2 = 26
6
P (E) = n(E)
n(S)
= 228 = .25

7. A committee of 8 is to be formed from a group of 7 mothers, 6 fathers,

and 8 children. What is the probability that the committee will have
exactly 4 fathers?
18 CHAPTER 3. PROBABILITY

Solution: The sample space consists of all possible committees of 8,

from total of n = 7 + 6 + 8 = 21 people. Committee selection is an
unordered selection.
The number of such committees n(S) =21 C8 .
Let E =be the event that there would be 4 fathers
(and hence 4 others from 7 + 8 = 15).
So, n(E) = (6 C4 )(15 C4 )
So, P (E) = n(E)
n(S)
= (6 C421)(C158 C4 ) .

8. The 6 seats in the first row are to be assigned to a class of 17 women

and 20 men. What is the probability that all the seats will be assigned
to women.

Solution: Seat assignment is an ordered selection.

Total number of such assignment is
n(S) =37 P6 .
Let E =be the event that all seat would be assigned to women.
n(E) =17 P6
So, P (E) = n(E)
n(S)
= 17 P6
37 P6
.

3.5 Conditional Probability and Independence

1. For two events, E and F, it is given that the probabilities P (E) = 0.6,
P (F |E) = 0.3, and P (F ) = 0.7. What is the probability that E and F
occur simultaneously?

Solution: P (E and F ) = P (F |E)P (E) = (0.3) ∗ (0.6).

2. For two events, E and F, it is given that the probabilities P (E) =

0.5, P (F and E) = 0.3, and P (F ) = 0.9. What is the conditional
probability that F occurred, given that E has occurred?

Solution: P (F |E) = P (F and E)/P (E) = 0.3/.05

3. Following are some data from a hospital emergency room:

(a) The probability that a patient in the emergency room will have
health insurance is 0.8.
3.5. CONDITIONAL PROBABILITY AND INDEPENDENCE 19

(b) The probability that a patient in the emergency room will survive
the treatment 0.9.
(c) The probability that a patient in the emergency room will have
health insurance and will also survive is 0.6.

What is the conditional probability that a patient in the emergency

room will survive, given that he/she has health insurance.

Solution: Let H = the event that the patient has Health insurance.
Let E = the event that the patient will survive.
Given P (H) = 0.8., P (E) = 0.9, P (H and E) = 0.6
P (E|H) = H Pand
(H)
E
= 0.6
0.8

4. Following are some observations on the stock market:

(a) The probability that the Dow Jones Industrial Average (DJIA)
will go up today is 0.75.
(b) The probability that the value of your portfolio will go up today
is 0.80.
(c) The probability that both the DJIA will go up and the value of
your portfolio will go up today is 0.6.

What is the conditional probability that the value of your portfolio

went up today, given that the DJIA went up today?

Solution: Let D = the event that DJIA will go up.

Let E = the event that your portfolio will go up.
Given P (D) = 0.75., P (E) = 0.80, P (D and E) = 0.6
P (E|D) = D Pand
(D)
E 0.6
= 0.75.

5. Following are some data on allergy treatment:

(a) The probability that a person will get the allergy in a season is
0.55.
(b) The probability that a person has taken an allergy treatment and
gets an allergy in the season is 0.15.
(c) The probability that a person has taken the treatment is 0.6.
20 CHAPTER 3. PROBABILITY

What is the conditional probability that a person will get an allergy,

given that she/he has taken the allergy treatment?

Solution: Let E = the event one would get the allergy in a season.
Let F = the event that one would have taken an allergy treatment.
Given P (E) = 0.55., P (F ) = 0.6, P (F and E) = 0.15
P (E|F ) = E Pand
(F )
F
= 0.15
0.6

6. Consider the following circuit with the ra-

dio: It is given that the probability that switch A is closed is 0.35 and
the probability that switch B is closed is 0.40. It is also known that
the 2 switches function independently. What is the probability that
the radio is playing?

Solution: E =event that switch-A is on.

F =event that switch-B is on. We compute P (E orF ).
We have P (E) = 0.35, P (F ) = 0.40.
P (E and F ) = P (E)P (F ) = .35 ∗ 40 = .14.
(Because of Independence.)
P (E or F ) = P (E) + P (F ) − P (E and F ) = .35 + .40 − .14 = .61.

7. An airplane has 2 engines and the engines function independently. The

probability that the first engine fails during a flight is 0.1 and the
probability that the second engine fails is 0.1. What is the probability
that both will fail during a flight?

Solution: E =event that Engine-1 is fails.

F =event thatEngine-1 is fails.
We have P (E) = 0.1, P (F ) = 0.1.
We compute P (E and F )P (E)P (F ) = (.1) ∗ (.1)
3.5. CONDITIONAL PROBABILITY AND INDEPENDENCE 21

8. The probability that you will receive a wrong number call this week
is 0.2. The probability that you will receive a sales call this week is
0.5. The probability that you will receive a survey call this week is 0.3.
What is the probability that you will receive one of each this week?
(Assume independence.)

Solution: Let E = be the event that you receive a wrong number call
Let F = be the event that you receive a sales call
Let G = be the event that you receive a survey call
P (E and F and G) = P (E)P (F )P (G) = (0.2.) ∗ (0.5) ∗ (0.3)

9. The probability that you will receive a wrong number call this week is
0.1. The probability that you will receive a sales call this week is 0.6.
What is the probability that you will receive either a wrong number
call or a sales call this week? (Assume independence.)

Solution: Let E = be the event that you receive a wrong number call
Let F = be the event that you receive a sales call
P (E) = 0.1, P (F ) = 0.6.
P (E or F ) = P (E)+P (F )−P (E and F ) = P (E)+P (F )−P (E)P (F ) =
0.1 + 0.6 + (0.1) ∗ 0.6).

10. During your trip to Florida, the probability that the weather in Florida
will be good is 0.9 and the probability that it will be cold in Lawrence
is 0.3. What is the probability that, during your trip, you will have
good weather in Florida and it will be cold in Lawrence? (Assume
independence.)

Solution: Let E = be the event that weather in Florida will be good

Let F = be the event that it will be cold in Lawrence
P (E and F ) = (0.9) ∗ (0.3).
22 CHAPTER 3. PROBABILITY
Chapter 4

Random Variables

4.1 Random Variables

None

4.2 Probability Distribution

1. The following table gives the probability distribution of the starting
salary X earned by new graduates from some university (to the nearest
$10K).

X=x 0 1 2 3 4 5 6 7
p(x) 0.05 0.15 0.22 0.22 0.17 0.10 .05 .04

What is the expected starting salary of a new graduate?

P
Solution: E(X) = µ = xi p(xi ) =
= 0∗.05+1∗.15+2∗.22+3∗.22+4∗.17+5∗.10+6∗.05+7∗.04 = 3.01

2. For the starting salary X in Question 1, what is the standard deviation

of the staring salary?

23
24 CHAPTER 4. RANDOM VARIABLES

Solution:P Variance
σ == x2i p(xi ) − µ2 =
2

[0 ∗ .05 + 1 ∗ .15 + 4 ∗ .22 + 9 ∗ .22 + 16 ∗ .17 + 25 ∗ .10 + 36 ∗ .05 + 49 ∗

.04] − (3.01)2 = 2.9299 √ √
So, standard Deviation σ = σ 2 = 2.9299 = 1.7117

3. Maria is a plumber who works for 3 different employers. Employer

A pays her $120 a day, employer B pays her $70 dollars a day, and
employer C pays her $180 a day. She works for whoever calls her first.
The probability that employer A calls her first is 0.4, the probability
that employer B calls first is .2, and the probability that employer C
calls her first is 0.3 (the probability that no one calls is .1). What is
the expected income of Maria per day?

Solution: Let X = Income of Maria on a day.

So, X takes values 0, 120, 70, 180. The probability function is given
by p(0) = .1, p(120) = .4, p(70) = .2, p(180) = .3.
In a tabular form, the distibution of Maria’s income is given by

X = x 0 120 70 180
p(x) .1 .4 .2 .3
P
So, mean E(X) = µ = xi p(xi ) =
0 ∗ p(0) + 120 ∗ p(120) + 70 ∗ p(70) + 180 ∗ p(180)
= 0 ∗ 0 + 120 ∗ .4 + 70 ∗ .2 + 180 ∗ .3 = 116

4. Maria is the plumber in Question 3. What is the standard deviation of

the daily income of Maria?

Solution: Variance σ 2 = s x2i p(xi ) − µ2

P
= [0 ∗ 0 + 14400 ∗ .4 + 4900 ∗ .2 + 32400 ∗ .3] − (116)2 = 3004
√ √
So, standard Deviation σ = σ 2 = 3004

5. The number X of typos in a website has the following probability dis-

tribution.

X=x 0 1 2 3 4 5
p(x) .14 0.27 0.27 0.18 0.09 0.05
What is the expected number of typos in a website?
4.2. PROBABILITY DISTRIBUTION 25

Solution:
P The mean
µ= xi p(xi ) = 0 ∗ p(0)+ 1∗ p(1)+ 2∗ p(2)+ 3∗ p(3)+ 4∗ p(4)+ 5∗ p(5)
== 0 ∗ .14 + 1 ∗ .27 + 2 ∗ .27 + 3 ∗ .18 + 4 ∗ .09 + 5 ∗ .05 = 1.96
6. Let X be the number of typos, as in Question 5. What is the standard
deviation of X?

Solution: Variance σ 2 = x2i p(xi ) − µ2

P
= (0 ∗ p(0) + 1 ∗ p(1) + 4 ∗ p(2) + 9 ∗ p(3) + 16 ∗ p(4) + 25 ∗ p(5)]−(1.96)2
= (0 ∗ .14 + 1 ∗ .27 + 4 ∗ .27 + 9 ∗ .18 + 16 ∗ .09 + 25 ∗ .05) − (1.96)2 =
5.66 − 4.8416 = 1.8184
√ √
So, standard Deviation σ = σ 2 = 1.8184
7. Let X be the number of typos, as in Question 5. What is the probability
that there would be at least 3 typos is a book?

Solution:
P (3 ≤ X) = P (X = 3) + P (X = 4) + P (X = 5) = 0.18 + 0.09 + 0.05
8. Let X represents the number of students in a class, in a school district.
The following is the distribution of X:

X = x 11 12 13 14 15 16 17 18 19 20 21
p(x) .08 .09 .11 .13 .14 .13 .10 .09 .06 .05 .02

What is the expected number of students in a class?

Solution:
X
E(X) = µ = xi p(xi ) = 11 ∗ .08 + 12 ∗ .09 + 13 ∗ .11 + · · · = 15.27

9. Refer to Question 8. Compute the standard deviation σ.

Solution: The varience

X 
σ2 = x2i p(xi ) −µ2 = (112 ∗ .08 + 122 ∗ .09 + 132 ∗ .11 + · · · −(15.27)2

= 240.03 − 233.1729 = 6.8571

So, the St. deviation
√ √
σ= σ2 = 6.8571 = 2.6186
26 CHAPTER 4. RANDOM VARIABLES

10. A Gambling house has a loaded die. One pays $3 to play each time.
One gets back number of dollars equal to the face that turns up. The
following is the probability distribution of the loaded die, together with
the win X.
F ace 1 2 3 4 5 6
p(x) .3 .2 .2 .1 .1 .1
W in X = x −2 −1 0 1 2 3
Compute the expected win E(X)?

Solution: The
P mean,
E(X) = µ = xi p(xi ) = (−2)∗.3+(−1)∗.2+0∗.2+1∗.1+2∗.1+3∗.1 =
−2

4.3 The Bernoulli and Binomial Experiments

1. The statistics of campus interviews show that for every 10 interviews 4
job offers are made. Out of 66 interviews, what is the probability that
at least 30 offers would be made? (Use TI-84, Silver Edition.)
4
Solution: Here n = 66, p = 10 = .4
P (30 ≤ X) = 1 − P (X ≤ 29)
= 1 − binomialcdf (66, .4, 29) = 1 − .7829 = .2171

2. Refer to Question 1. What would be the expected number of job offers

made?

Solution: mean µ = E(X) = np = 66 ∗ .4 = 26.4

3. Refer to Question 1. What would be the standard deviation σ of the

number of job offers made?

Solution:
p StandardpDeviation
σ = np(1 − p) = 66 ∗ .4 ∗ (1 − .6) = 3.9799

4. Assume that 20 percent of the babies get fever after immunization

shoots. If 130 babies are immunized in a clinic, what is the probability
that at most 30 will get fever?
4.3. THE BERNOULLI AND BINOMIAL EXPERIMENTS 27

Solution: Here n = 130, p = .2

P (X ≤ 30) = binomialcdf (130, .2, 30) = .8384

5. Refer to Question 4. What is the expected number of babies that would

get fever?

Solution: mean µ = E(X) = np = 130 ∗ .2 = 26

6. Refer to Question 4. What would be the standard deviation σ ?

Solution:
p StandardpDeviation
σ = np(1 − p) = 130 ∗ .2 ∗ (1 − .2) = 4.5607

7. It is assumed by the coach that a swimmer can finish an event within

target time 45 percent times during practice. Suppose the swimmer
swims 80 times. What is the probability that he/she will finish within
the target time at least 40 times?

Solution: Here n = 80, p = .45

P (40 ≤ X) = 1 − P (X ≤ 39) = 1 − binomialcdf (80, .45, 39)
= 1 − .7846 = .2154

8. Refer to Question 8. What is the expected number E(X) of times that

he/she will finish within target time?

Solution: mean µ = E(X) = np = 80 ∗ .45

9. Refer to Question 8. What is the standard deviation σ of the number

of times X that he/she will finish within target time?

Solution:
p StandardpDeviation
σ = np(1 − p) = 80 ∗ .45 ∗ (1 − .45)

10. It was reported, that 20 percent of the population in a region were

infected by AIDS-HIV. A sample of 200 people from this region were
examined for AIDS-HIV. What was the expected number of infected
people?
28 CHAPTER 4. RANDOM VARIABLES
Chapter 5

Continuous Random Variables

5.1 Probability Density Function (pdf)

None

5.2 The Normal Random Variable

Use TI-84 "Normalcdf" function, under DISTR tab.

1. Suppose Z is the standard normal random variable. Find the proba-

bility P (−1.23 ≤ Z).

Solution: P (−1.23 ≤ Z) = normalcdf (−1.23, 5) = .8907

2. Suppose Z is the standard normal random variable. Find the proba-

bility P (−1.18 ≤ Z ≤ 1.87).

Solution: P (−1.18 ≤ Z ≤ 1.87) = nomalcdf (−1.18, 1.87) = .8501

3. Suppose X is a normal random variable with mean µ = 11.5 and stan-

dard deviation σ = 2.3. Find the probability P (X ≤ 14).

29
30 CHAPTER 5. CONTINUOUS RANDOM VARIABLES

Solution:
P (X ≤ 14) = P
X−µ ≤ 14−µ


σ σ
= P Z ≤ 14−11.5
2.3
= P (Z ≤ 1.0870) = nomalcdf (−5, 1.0870) = .8615
4. Monthly consumption of electricity X (in KWH, in a winter month) by
the households in a county has a normal distribution with mean 875
KWH and standard deviation 155 KWH. What proportions of house-
holds consumes less than 1000 KWH?

Solution:
P (X ≤ 1000) = P
X−µ ≤ 1000−µ


σ σ
= P Z ≤ 1000−875
155
= P (Z ≤ .8065) = nomalcdf (−5, 1.0870) = .7900
5. The monthly cell phone minutes used by an individual in a city has
normal distribution with mean 2700 minutes and standard deviation
325 minutes. What proportion of calls would last more than 3000
minutes?

Solution:
P (3000 ≤ X) = P
3000−µ ≤ X−µ


σ σ
= P 3000−2700
325
≤ Z = P (.9231 ≤ Z) = normalcdf (.9231, 5) = .1780
6. The amount of time a student spends to take a test has normal dis-
tributions with mean 45 minutes and standard deviation 13 minutes.
What proportion of students would finish in 60 minutes?

Solution:
P (X ≤ 60) = P
X−µ 60−µ


σ
≤ σ
= P Z ≤ 60−45
13
= P (Z ≤ 1.1538) = nomalcdf (−5, 1.1538) = .8757
7. The annual rainfall X in a region is normally distributed with mean
µ = 62 cm and standard deviation σ = 9 cm. What is the probability
that rainfall will be between 55 cm and 70 cm?

Solution:
P (55 ≤ X ≤ 70) = P 55−µ ≤ X−µ ≤ 70−µ = P 55−62 ≤ Z ≤ 70−62



σ σ σ 9 9
= P (−.7778 ≤ Z ≤ .8889) = nomalcdf (−.7778, .8889) = .5946
8. The birth weight X of babies is normally distributed with mean µ = 113
ounces and standard deviation σ = 19 ounces. What proportion of
babies will have birth weight below 150 ounces?
5.2. THE NORMAL RANDOM VARIABLE 31

Solution:
P (X ≤ 150) = P
X−µ ≤ 150−µ


σ σ
= P Z ≤ 150−113
19
= P (Z ≤ 1.9474) = nomalcdf (−5, 1.9474) = .9743

9. The length X of babies at birth is normally distributed with mean

µ = 18.5 inches and standard deviation σ = 2.3 inch. What proportion
of babies are smaller than 21 inches ?

Solution:
P (X ≤ 21) = P
X−µ ≤ 21−µ


σ σ
= P Z ≤ 21−18.5
2.3
= P (Z ≤ 1.0870) = nomalcdf (−5, 1.0870) = .8615

10. The weight X of salmon caught in a river is normally distributed with

mean µ = 24 pounds and standard deviation σ = 7 pounds. You
can keep only those above 15 pounds. What proportion of the salmon
caught can be kept?

Solution:
P (15 ≤ X) = P
15−µ X−µ


σ
≤ σ
= P 15−24
7
≤ Z = P (−1.4286 ≤ Z) = normalcdf (−1.4286, 5) = .9234

5.2.1 Inverse Normal

Use TI-84 "invNorm" function, under DISTR tab.

1. Suppose Z is the standard normal random variable. It is given that

P (Z ≤ c) = 0.2300. What is the value of c?

Solution:
Answer = invN orm(.23) = −.7388

2. Suppose Z is the standard normal random variable. It is given that

P (d ≤ Z) = 0.9500. What is the value of d?

Solution:
P (d < Z) = .95
P (Z ≤ d) = .05
Answer = invN orm(.05) = −1.6449
32 CHAPTER 5. CONTINUOUS RANDOM VARIABLES

3. Suppose X is a normal random variable with mean µ = 3.5 pounds

and standard deviation σ = 1.2 pounds. Given that the probability
P (c ≤ X) = 0.2550, what is the value of c? Solution: µ = 3.5, σ = 1.2
P (c < X) = 0.2550
P (X < c) = 1 − .2550 = .745

P Z < c−µ


σ
= .745 (This step iscalled Standardization)
P (Z < .6588) = .745 Because invN orm(.745) = .6588
Compare:
c−µ c − 3.5
= = .6588 =⇒ c = 3.5 + 1.2 ∗ .6588 = 4.2906
σ 1.2
4. The weight X of babies (of a fixed age) is normally distributed with
mean µ = 212 ounces and standard deviation σ = 25 ounces. Doctors
would be concerned (not necessarily alarmed) if a baby is among the
lower 5 percent in weight. Find the cut-off weight l, below which the
doctors will be concerned.

Solution: µ = 212, σ = 25,

P (X < c) = 0.05

P Z < c−µ


σ
= 0.05 (This step iscalled Standardization)
P (Z < −1.6449) = 0.05 Because invN orm(.05) = −1.6449
Compare:
c−µ c − 212
= = −1.6449 =⇒ c = 212 − 25 ∗ .1.6449 = 170.8775
σ 25
5. The weight X of babies (of a fixed age) is normally distributed with
mean µ = 212 ounces and standard deviation σ = 25 ounces. Doctors
would also be concerned (not necessarily alarmed) if a baby is among
the upper 10 percent in weight. Find the cut-off weight u, above which
the doctors will be concerned.

Solution: µ = 212, σ = 25,

P (u < X) = 0.10. So, P (X < u) = .90

P Z < u−µ


σ
= .90 (This step iscalled Standardization)
P (Z < 1.2816) = .90 Because invN orm(.90) = 1.2816
5.2. THE NORMAL RANDOM VARIABLE 33

Compare:

u−µ u − 212
= = 1.2816 =⇒ u = 212 + 25 ∗ 1.2816 = 244.04
σ 25

6. The weight X of salmon caught in a river is normally distributed with

mean µ = 24 pounds and standard deviation σ = 6 pounds. You can
keep those that are among that upper 66 percent in weight. What is
the cut-off weight l, above which you can keep the fish?

Solution: µ = 24, σ = 6,
P (l < X) = .66. So, P (X < l) = 1 − .66 = .34

P Z < i−µ


σ
= .34 (This step iscalled Standardization)
P (Z < −.4125) = .34 Because invN oem(.34) = −.4125
Compare:

l−µ l − 24
= = −.4125 =⇒ l = 24 − .4125 ∗ 6 = 21.525
σ 6

7. The height of an adult male in a region is known to be normally dis-

tributed with mean of µ = 69 inches and a standard deviation σ = 2.5
inches. How high should a doorway be so that 92 percent of adult males
can pass through it without having to bend?

Solution: µ = 69, σ = 2.5,

P (X < u) = .92

P Z < u−µ


σ
= .92 (This step iscalled Standardization)
P (Z < 1.4051) = .92 Because invN oem(.92) = 1.4051

Compare:

u−µ u − 69
= = 1.4051 =⇒ u = 69 + 1.4051 ∗ 2.5 = 72.5128
σ 2.5

8. The hourly wages X in an industry has a normal distribution with

mean $40 and standard deviation $17. What is the 97 percentile of the
hourly wage?
34 CHAPTER 5. CONTINUOUS RANDOM VARIABLES

Solution: µ = 40, σ = 17,

P (X < u) = .97

P Z < u−µ


σ
= .97 (This step iscalled Standardization)
P (Z < 1.8808) = .97 Because invN oem(.97) = 1.8808
Compare:
u−µ u − 40
= = 1.8808 =⇒ u = 40 + 1.8808 ∗ 17 = 71.9736
σ 17
9. The mean monthly water consumption X by the households in a subdi-
vision has a normal distribution with mean 4500 gallons and standard
deviation 3000 gallons. A surcharge would be imposed to the top 20
percent users. What is the cut-off number of gallons?

Solution: µ = 4500, σ = 3000,

P (u < X) = .20. So, P (X < u) = .80

P Z < u−µ


σ
= 80 (This step iscalled Standardization)
P (Z < .8416) = .80 Because invN oem(.80) = .8416
Compare:
u−µ u − 4500
= = .8416 =⇒ u = 4500 + .8416 ∗ 3000 = 7024.8
σ 3000

10. The time X needed for a student to arrive at the class from his/her
residence has a normal distribution with mean 30 minutes and with
standard deviation 7 minutes. How much time before the class he/she
should start so that he/she would be late only for 7 percent of the first
period?

Solution: µ = 30, σ = 7,
P (u < X) = .07. So, P (X < u) = .93

P Z < u−µ


σ
= .93 (This step iscalled Standardization)
P (Z < 1.4760) = .93 Because invN oem(.93) = 1.4760
Compare:
u−µ u − 30
= = 1.4760 =⇒ u = 30 + 7 ∗ 1.4760 = 40332
σ 7
5.3. NORMAL APPROXIMATION TO BINOMIAL 35

5.3 Normal Approximation to Binomial

1. These are problems from Sec 5.3 Normal approximation to binomial.
n = 600, p = .40
meanpµ = np = 600√∗ .4 = 240
σ = np(1 − p) = 600 ∗ .4 ∗ .6 = 12
= P (220 < X) = P (221 ≤ X) = P (220.5 < X)
(continuity correction.)  
220.5−µ
)<Z =P √ 220.5−240


=P σ
)<Z
(600∗.4∗.6
= P (−1.625 < Z) = normalcdf (−1.625, 5) = .9479

2. This is a problem from Sec 5.3 Normal approximation to binomial.

p = .42, n = 800,
p = 800 ∗ .42 =
µ = np √ 336
σ = np(1 − p) = 800 ∗ .42 ∗ 58 = 13.9599

P (X ≤ 360) = P (X < 360.5)

(continuity correction.)
= P Z < 360.5−µ = P Z < 360.5−336



σ 13.9599
= P (Z < 1.7550) = normalcdf (−5, 1.7550) = .9604

3. This is a problem from Sec 5.3 Normal approximation to binomial.

p = .2, n = 400
p = 400 ∗ .2 =√80
µ = np
σ = np(1 − p) = 400 ∗ .2 ∗ .8 = 8
P (X < 74) = P (X ≤ 73) = P (X < 73.5)
(continuity correction.)
= P Z < 73.5−µ = P Z < 73.5−80



σ 8
= P (Z < [73.5 − 80]/8)
= P (Z < −.8125) = normalcdf (−5, −.8125) = 0.2083

4. These are problems from Sec 5.3 Normal approximation to binomial.

n = 256, p = .20
µ = npp= 256 ∗ .2 = 51.2
√
σX = np(1 − p) = 256 ∗ .2 ∗ .8
P (60 < X) = P (61 ≤ X) = P (60.5 < X)
(continuity correction.) 
60.5−µ 60.5−51.2


=P σ
<Z =P √
256∗.2∗.8
<Z
36 CHAPTER 5. CONTINUOUS RANDOM VARIABLES

= P (1.4531 < Z) = normalcdf (1.4531, 5) = .0731

5. Here p = .15, n = 60
p = 60 ∗ .15 =√9
µ = np
σ = np(1 − p) = 60 ∗ .15 ∗ .85 = 2.7659

P (X ≤ 10) = P (X < 10.5) = P (Z < 10.5−µ 10.5−9

σ
=P Z< 2.7659
= P (Z < .5423) = normalcdf ((−5, .5423) = .7062

6. Here p = .6, n = 150.

p = 150 ∗ .6 =√90
µ = np
σ = np(1 − p) = 150 ∗ .60 ∗ .40 = 6
79.5−µ


P (X < 80) =
P (X ≤ 79) = P (X < 79.5) = P Z < σ
=
P Z < 79.5−90
6
= P (Z < −1.75) = normalcdf (−5, −1.75) = 0.0401

7. Here p = .55, n = 780

p = 780 ∗ .55 =
µ = np √ 429
σ = np(1 − p) = 780 ∗ .55 ∗ .45 = 13.8942
450.5−µ


P (450 < X) =
P (451 ≤ X) = P (450.5 < X) = P σ
<Z =
P 450.5−429
13.8942
<Z
= P (1.5474 < Z) = normalcdf (1.5474, 5) = .0609

8. Here p = .22, n = 600

p = 600 ∗ .22 =
µ = np √ 132
σ = np(1 − p) = 600 ∗ ..22 ∗ .78 = 10.1469
P (130 < X) = P (131 ≤ X) = P (130.5
< X)
130.5−µ
< Z = P 130.5−132


=P σ 10.1469
<Z
= P (−.1478 < Z) = normalcdf (−.1478, 5) = .5587

9. Here p = .73, n = 400.

p = 400 ∗ .73 =
µ = np √ 292
σ = np(1 − p) = 400 ∗ 73 ∗ .27 = 8.8792
P (X < 300) = P
(X ≤ 299) = P (X <
299.5)
= P Z < 299.5−µ
σ
= P Z < 299.5−292
8.8792
= P (Z < .8447) = normalcdf (−5, .8447) = .8009

10. Here p = .25, n = 220.

p = 220 ∗ .25 =
µ = np √ 55
σ = np(1 − p) = 220 ∗ .25 ∗ .75 = 6.4226
5.3. NORMAL APPROXIMATION TO BINOMIAL 37

P (X< 50) = P (X  ≤ 49) = P (X <
49.5)

49.5−µ]
=P Z< σ = P Z < 49.5−55
6.4226
= P (Z < −8564) = normalcdf (−5, −8564) = .1959
38 CHAPTER 5. CONTINUOUS RANDOM VARIABLES
Chapter 6

Elements of Sampling
Distribution

6.1 Sampling Distribution

None

6.2 Central Limit Theorem

1. We are asked to compute P (1600 < X).
The sample size n = 64. we use mean of µ = 1550, and
σX = √σn = √41664
= 52
 
1600−µ
So, P (1600 < X) = P σX
<Z
1600−1550


=P 52
< Z = P (.9615 < Z)
= normalcdf (.9615, 5) = .1682

2. We compute P (X < 230).

µ = 225 σ = 45, n = 68
we use mean of µ = 225, and

39
40 CHAPTER 6. ELEMENTS OF SAMPLING DISTRIBUTION

σX = √σ = √45
= 5.4571
n 68  
230−µ
So, P (X < 230) = P Z < σ
X

= P Z < 230−225


5.4571
= P (Z < .9162) = normalcdf (−5, .9162) = .8202

3. We compute P (X < 116).

µ = 114, σ = 18, n = 100
Use mean of µ = 114 and
σX = √σn = √18
100
= 1.8
 
So, P (X < 116) = P Z < 116−µ)
σX
116−114


= P Z < 1.8 = P (Z < 1.1111)
= normalcdf (−5, 1.1111) = .8667

4. We compute P (X < 36).

µ = 33, σ = 12, n = 35
Use mean of µ = 33 and
σX = √σn = √1235 = 2.0284
 
36−µ) 36−33


So, P (X < 36) = P Z < σ = P Z < 2.0284
X
= P (Z < 1.4790) = normalcdf (−5, 1.4790) = .9304

5. We are asked to compute P (50 < X).

Here, n = 77, µ = 48, σ = 19
Use mean of µ = 48, and
σX = √σn = √1977 = 2.1653
   
So, P (50 < X) = P 50−µ)
σX
< Z = P 50−48)
2.1653
< Z
= P (.9237 < Z) = normalcdf (.9237, 5) = .1778

6. This question is posed in terms of ’Total’.

Note sample mean = X = T otal n
.
Question is P (T otal < 3000) =?
We change the problem to:
P (T otal < 3000) = P ( T otal < 3000


n n
= P (X < 3000/98) = P (X < 30.6122)
µ = 28, σ = 18, n = 98
we use mean of X = mean = 28 and
σX = √σn = √1898 = 1.8183
6.2. CENTRAL LIMIT THEOREM 41
 
So, P (X < 30.6122) = P Z < 30.6122−µ)
σX
 
30.6122−28)
=P Z< σX
= P (Z < [30.6122 − 28]/1.8183) = P (Z < 1.4366)
= normalcdf (−5, 1.4366) = .9246
7. This question is posed in terms of ’Total’.
Note sample mean = X = T otaln
.
Question is P (900 < T otal) =?
We change the problem to:
P (900 < T otal) = P 900 T otal


n
< n
= P 900


36
< X = P (25 < X)
µ = 24, σ = 8, n = 36
Use mean of µ = 24 and
σX = √σn = 36 8
= 1.3333
 
So, P (25 < X) = P 25−µ)
σX
< Z
 
25−24)
= P 1.3333 < Z = P (.7500 < Z)
= normalcdf (.7500, 5) = .2266
8. This question is posed in terms of ’Total’.
Note sample mean = X = T otaln
.
Question is P (130 < T otal) =?
We change the problem to:

P (130 < T otal) = P 130 T otal

n
< n
= P 10.8333 < X
µ = 10, σ = 4.4, n = 12

Use mean µ = 10 and

σX = √σn = 4.4
12
= 1.2702
 
So, P (10.8333 < X) = P 10.8333−µ
σX
< Z
 
10.8333−10
=P 1.2702]
< Z = P (.6560 < Z)
= normalcdf (.6560, 5) = .2559
9. This question is posed in terms of ’Total’.
Note sample mean = X = T otaln
.
Question is P (T otal < 1800) =?
42 CHAPTER 6. ELEMENTS OF SAMPLING DISTRIBUTION

We change the problem to:

P (T otal < 1800) = P T otal 1800 T otal 1800

n
< n
== P n
< 33
P X < 54.5455
Here µ = 55, σ = 22, n = 33
Use µ = 55 and
σX = √σn = 2233
= 3.8297
 
54.5455−µ 54.5455−55


So, P (X < 54.5455)P Z < σX
= P Z < 3.8297
= P (Z < −.1187) = normalcdf (−5, −.1187) = .4528
10. This question is posed in terms of ’Total’.
Note sample mean = X = T otaln
.
Question is P (6000 < T otal) =?
We change the problem to:

P (6000 < T otal) = P 6000 < T otal

30 n
= P 200 < X
Here µ = 220, σ = 100, n = 30
Use µ = 220 and
σX = √σn = 10030
= 18.2574
 
So, P (200 < X) = P 200−µσX
< Z
200−220


= P 18.2574 < Z = P (−1.0954 < Z)
= normalcdf (−1.0954, 5) = .8633

6.3 Distribution of the Sample Proportion

1. These are problems on Sample Proportion to be solved using CLT.
Write X = Number of success.
We are asked to find P (400 < X).
Here sample
q size nq= 680, p = .58
p(1−p) .58∗.42
σX = n
= 680
400
< Xn = 400



P (400 < X) = P n
P 680
<X 
 
400/680−p 400/680−.58
=P σ
<Z =P √ <Z
X .58∗.42/680
= P (.4351 < Z) = normalcdf (.4351, 5) = .3317
2. These are problems on Sample Proportion to be solved using CLT.
6.3. DISTRIBUTION OF THE SAMPLE PROPORTION 43

Write X = Number of success. We are asked to find P (X < 300).

Here sample
q size n = 480, p = .65
p(1−p)
p
σX = n
= .65 ∗ .35/480
P (X< 300) = P n <300
X
= P X< 300



n 480
300 300
−p −.65
= P Z < 480σ = P Z < 480σ
X X
= P (Z < −1.1483) = normalcdf (−5, −1.1483) = .1254

3. These are problems on Sample Proportion to be solved using CLT.

Write X = Number of success. We are asked to find P (X < 150).
Here sample
q size n = 200, p = .72
p(1−p)
p
σX = n
= .72 ∗ .28/200
X
P (X < 150) = P n <1 150 = P X < 150



n 200

150 150
 
−p −.72
=P Z< σ 200
=P Z< √ 200
X (.72∗.28/200)
= P (Z < .9449) = normalcdf (−5, .9449) = .8276

4. These are problems on Sample Proportion to be solved using CLT.

Write X = Number of success. We are asked to find P (370 < X) .
Here sample
q size n = 720, p = .52
σX = p(1−p)
p
n
= .52 ∗ .48/720
P (370 < X) = P 370 X



< = P 400/720 < X
 370  n  n 370 
−p −.52
=P 720
σ
<Z =P √ 720
<Z
X .52∗.48/720
= P (.3282 < Z) = normalcdf (−.3282, 5) = .6286

5. These are problems on Sample Proportion to be solved using CLT.

Write X = Number of success. We are asked to find P (100 < X) .
Here sample
q size n = 120, p = .80
p(1−p)
p
σX = n
= .80 ∗ .20/120

< X) = P 100 < Xn = P 100

P (100
 100 n 120
<X
100
−p −.80
= P 120σ < Z = P 120σ <Z
X X
= P (.9128 < Z) = normalcdf (.9128, 5) = .1807

6. These are problems on Sample Proportion to be solved using CLT.

Write X = Number of success. We are asked to find P (X < 100) .
44 CHAPTER 6. ELEMENTS OF SAMPLING DISTRIBUTION

Here sample
q size n = 250, p = .43
σX = p(1−p)
p
n
= .43 ∗ .57/250
X
P (X < 100) = P n <100 100



n
= P X < 250

100 100
 
−p −.43
=P Z< σ 250
=P Z< √ 250
X .43∗.57/250
= P (Z < −.9581) = normalcdf (−5, −.9581) = .1690

7. These are problems on Sample Proportion to be solved using CLT.

Write X = Number of success. We are asked to find P (X < 215) .
Here sample
q size n = 800, p = .25
p(1−p)
p
σX = n
= .25 ∗ .75/800
P (X < 215) = P n <215
X
= P X < 215



n 800

215 215
 
−p −.25
=P Z< σ 800
=P Z< √ 800
X .25∗.75/800
= P (Z < 1.2247) = normalcdf (−5, 1.2247) = .8896

8. These are problems on Sample Proportion to be solved using CLT.

Write X = Number of success. We are asked to find P (X < 100) .
Here sample
q size n = 700, p = .15
σX = p(1−p)
p
n
== .15 ∗ .85/700
P (X < 100) = P n <100
X 100



n
= P X < 700

100 100
 
−p −.15
=P Z< σ 700
=P Z< √ 700
X .15∗.85/700
= P (Z < −.5293) = normalcdf (−5, −.5293) = .2983
Chapter 7

Estimation

7.1 Point and Interval Estimation

7.1.1 Confidence Interval of µ

1. Here the population standard deviation σ = 10

the sample size n = 49
the sample mean X = 100
Level of confidence 99 percent. So,
1 − α = .99, α/2 = .005. Therefore,
zα/2 = z.005 = invN ormal(1 − .01) = 2.5758
z σ
MOE= α/2 √
n
= 2.5758∗10
√
49
= 3.6797
LEP= X − E = 100 − 3.6797
LEP= X + E = 100 + 3.6797

2. Here the population standard deviation σ = 13.5

the sample size n = 87
the sample mean X = 68
Level of confidence 96 percent. So,
1 − α = .96 α/2 = .02. Therefore,
zα/2 = z.02 = invN ormal(1 − .02) = 2.0537

45
46 CHAPTER 7. ESTIMATION

z σ
MOE= α/2
√
n
= 2.0537∗13.5
√
87
= 2.9724
LEP= X − E = 68 − 2.9724
LEP= X + E = 68 + 2.9724

3. Here the population standard deviation σ = 7.5

the sample size n = 116
the sample mean X = 22
Level of confidence 98 percent. So,
1 − α = .98 α/2 = .01. Therefore,
zα/2 = z.01 = invN ormal(1 − .01) = 2.3263
z σ
MOE= α/2 √
n
= 2.3263∗7.5
√
116
= 1.6199
LEP= X − E = 22 − 1.6199
LEP= X + E = 22 − 1.6199

4. Here the population standard deviation σ = 3.5

the sample size n = 30
the sample mean X = 25
Level of confidence 95 percent. So,
1 − α = .95 α/2 = .025. Therefore,
zα/2 = z.∗∗ = invN ormal(1 − .025) = 1.9600
z σ
MOE= α/2 √
n
= 1.9600∗3.5
√
30
= 1.2525
LEP= X − E = 25 − 1.2525
LEP= X + E = 25 + 1.2525

5. Here the population standard deviation σ = 1278

the sample size n = 180
the sample mean X = 4200
Level of confidence 92 percent. So,
1 − α = .92 α/2 = .04. Therefore,
zα/2 = z.04 = invN ormal(1 − .04) = 1.7507
z σ
MOE= α/2 √
n
= z1.7507∗1278
√
180
= 166.7655
LEP= X − E = 4200 − 166.7655
LEP= X + E = 4200 + 166.7655

6. Here the population standard deviation σ = 6

the sample size n = 56
the sample mean X = 21.1
7.1. POINT AND INTERVAL ESTIMATION 47

Level of confidence 90 percent. So,

1 − α = .90 α/2 = .05. Therefore,
zα/2 = z.05 = invN ormal(1 − .05) =
z σ z σ
MOE= α/2 √
n
= α/2
√
n
= 1.6449
LEP= X − E = 21.1 − 1.6449
LEP= X + E = 21.1 + 1.6449

7.1.2 The Required Sample Size

1. Here the population standard deviation σ = 45
and maximum error E = 5
Level of confidence 99 percent. So
1 − α = .99 α/2 = .005. Therefore,
zα/2 = z.01 = invN ormal(1 − .005) = 2.5758
z σ
2
2
The sample size n = α/2 E
= 2.5758∗45
5
= 537.41
We would round it upward. So, Answer = 538

2. Here the population standard deviation σ = 20

and maximum error E = 2
Level of confidence 98 percent. So
1 − α = .98 α/2 = .01. Therefore,
zα/2 = z.01 = invN ormal(1 − .01) = 2.3263
z σ
2 2.3263∗20 2


The sample size n = α/2 E
= 2
= 541.17
We would round it upward. So, Answer = 542

3. Here the population standard deviation σ = 13

and maximum error E = 1
Level of confidence 96 percent. So
1 − α = .96 α/2 = .02. Therefore,
zα/2 = z.02 = invN ormal(1 − .02) = 2.0537
z σ
2
2
The sample size n = α/2 E
= 2.0537∗13
1
= 712.79
We would round it upward. So, Answer = 713

4. Here the population standard deviation σ = 87

and maximum error E = 5
Level of confidence 94 percent. So
1 − α = .94 α/2 = .03. Therefore,
48 CHAPTER 7. ESTIMATION

zα/2 = z.03 = invN ormal(1 − .03) = 1.8808

z σ
2 1.8808∗87 2


The sample size n = α/2 E
= 5
= 1070.99
We would round it upward. So, Answer = 1071

5. Here the population standard deviation σ = 540

and maximum error E = 100
Level of confidence 97 percent. So
1 − α = .97 α/2 = .015. Therefore,
zα/2 = z.015 = invN ormal(1 − .015) = 2.1701
z σ
2
2
The sample size n = α/2 E
= 2.1701∗540
100
= 137.32
We would round it upward. So, Answer = 138

6. Here the population standard deviation σ = 1.5 and maximum error

E = .5
Level of confidence 80 percent. So
1 − α = .80 α/2 = .1. Therefore,
zα/2 = z.1 = invN ormal(1 − .1) = 1.2816
z σ
2 1.2816∗1.5 2


The sample size n = α/2 E
= .5
= 14.78
We would round it upward. So, Answer = 25

7.2 Confidence interval for µ when σ is unknown

These are also known as T-intervals.

1. Here the sample size n = 22

the sample mean X = 155.1
Sample standard deviation s = 14.9
The degrees of freedom df = n − 1 = 22 − 1 = 21
Level of confidence: 95 percent. So
1 − α = .95 α/2 = .025. Therefore,
tn−1,α/2 = invT (1 − .025, 21) = 2.0796
t s
MOE= n−1,α/2
√
n
= 2.0796∗14.9
√
22
= 6.6062
LEP= X − E = 155.1 − 6.6062
LEP= X + E = 155.1 + 6.6062
7.2. CONFIDENCE INTERVAL FOR µ WHEN σ IS UNKNOWN 49

2. Here the sample size n = 250

the sample mean X = 129.1
Sample standard deviation s = 11.95
The degrees of freedom df = n − 1 = 250 − 1 = 249
Level of confidence: 99 percent. So
1 − α = .99 α/2 = .005. Therefore,
tn−1,α/2 = invT (1 − .005, 249) = 2.5957
t s
MOE= n−1,α/2
√
n
= 2.5957∗11.95
√
249
= 1.9657
LEP= X − E = 129.1 − 1.9657
LEP= X + E = 129.1 − 1.9657
3. Here the sample size n = 131
the sample mean X = 101.6
Sample standard deviation s = 11.1
The degrees of freedom df = n − 1 = 131 − 1 = 130
Level of confidence: 96 percent. So
1 − α = .96 α/2 = .02. Therefore,
tn−1,α/2 = invT (1 − .02, 130) = 2.0746
t s
MOE= n−1,α/2
√
n
= 2.0746∗11.1
√
131
= 2.0120
LEP= X − E = 101.6 − 2.0120
LEP= X + E = 101.6 + 2.0120
4. I used TI-84 to summarize the data:
the sample size n = 18
the sample mean X = 4145.11
Sample standard deviation s = 2219.86
The degrees of freedom df = n − 1 = 18 − 1 = 17
Level of confidence: ?? percent. So
1 − α = .95 α/2 = .025. Therefore,
tn−1,α/2 = invT (1 − .025, 17) = 2.1098
t s
MOE= n−1,α/2
√
n
= 2.1098∗2219.86
√
18
= 1103.90
LEP= X − E = 4145.11 − 1103.90
LEP= X + E = 4145.11 + 1103.90
5. I used TI-84 to summarize the data:
the sample size n = 19
the sample mean X = 51.3895
Sample standard deviation s = 2.6143
50 CHAPTER 7. ESTIMATION

The degrees of freedom df = n − 1 = 19 − 1 = 18

Level of confidence: 95 percent. So
1 − α = .95 α/2 = .025. Therefore,
tn−1,α/2 = invT (1 − .025, 18) = 2.1009
t s
MOE= n−1,α/2
√
n
= 2.1009∗2.6143
√
19
= 1.2600
LEP= X − E = 51.3895 − 1.2600
LEP= X + E = 51.3895 + 1.2600

6. Here the sample size n = 19

the sample mean X = 1.4684
Sample standard deviation s = .1924
The degrees of freedom df = n − 1 = 19 − 1 = 18
Level of confidence: 99 percent. So
1 − α = .99 α/2 = .005. Therefore,
tn−1,α/2 = invT (1 − .005, 18) = 2.8784
t s
MOE= n−1,α/2
√
n
= 2.8784∗.1924
√
19
= .1271
LEP= X − E = 1.4684 − .1271
LEP= X + E = 1.4684 + .1271

7.3 About the Population Proportion

1. Here sample size n = 180
The number of success T = 27
So, the sample proportion of success X = Tn = 180 27
= .15
Given level of confidence is 95 percent.
1 − α = .95, α/2r= .025, zα/2 = z.025 = invN ormal(1 − .025) = 1.9600
q
MOE= e = zα/2 X(1−X n
= 1.9600 ∗ .15(1−.15)
180
= .052164
LEP= X − e = .15 − .052164
LEP= X + e = .15 + .052164
z
Conservative MOE = E = √α/2 4n
= √1.9600
4∗180
= .073304
(In this section, for error terms, we retain at least 6 decimal points.)

2. Here sample size n = 176

The number of success T = 44
7.4. CONFIDENCE INTERVAL OF THE VARIANCE σ 2 51

44
So, the sample proportion of success X = Tn = 176 = .25
Given level of confidence is 99 percent.
1 − α = .99, α/2r= .005, zα/2 = z.005 = invN ormal(1 − .005) = 2.5758
q
X(1−X
MOE= e = zα/2 n
= 2.5758 ∗ .25(1−.25)
176
= .084073
LEP= X − e = .25 − .084073
LEP= X + e = .25 − .084073
z
Conservative MOE = E = √α/2 4n
= √2.5758
4∗176
= .097079
(In this section, for error terms, we retain at least 6 decimal points.)

3. Here given precision E = .01

Given level of confidence is 95 percent.
1 − α = .95, α/2 = .025, zα/2 = z.025 = invN ormal(1 − .025) = 1.9600
zα/2
2
2
The required sample size n = 2E = 1.9600
2∗.01
= 9604
4. Here given precision E = .02
Given level of confidence is 99 percent.
1 − α = .99, α/2 = .005, zα/2 = z.005 = invN ormal(1 − .005) = 2.5758
zα/2
2
2
The required sample size n = 2E = 2.5758
2∗.02
= 4146.7160 We would
round it upward. So,
Answer = 4147

7.4 Confidence Interval of the Variance σ 2

1. Use TI to compute
the sample size n = 28
the sample variance s2 2 = (12.3135)2 = 151.6223
Degrees of freedom df = n − 1 = 27
Given level of confidence is 95 percent.
1 − α = .95, α/2 = .025, Using the Inverse Chi-Square animation 7.4.1
we have
χ2n−1,α/2 = χ227,.025 = 43.195
χ2n−1,1−α/2 = χ227,1−.025 = 14.574
(n−1)s2 27∗151.6223
Therefore, LEP= χ2n−1,α/2
= 43.195
52 CHAPTER 7. ESTIMATION

(n−1)s2 27∗151.6223
REP = χ2n−1,1−α/2
= 14.574

2. the sample size n = 16

the sample variance s2 = 313
Degrees of freedom df = n − 1 = 17
Given level of confidence is 99 percent.
1 − α = .99, α/2 = .005, Using the Inverse Chi-Square animation 7.4.1
we have
χ2n−1,α/2 = χ217,.005 = 35.719
χ2n−1,1−α/2 = χ217,1−.005 = 5.698
(n−1)s2 17∗313
Therefore, LEP= χ2n−1,α/2
= 5.698
(n−1)s2 17∗313
REP = χ2n−1,1−α/2
= 5.698

3. Use TI to compute
the sample size n = 20
the sample variance s2 2 = (1.4162)2 = 2.0056
Degrees of freedom df = n − 1 = 19
Given level of confidence is 90 percent.
1 − α = .90, α/2 = .05, Using the Inverse Chi-Square animation 7.4.1
we have
χ2n−1,α/2 = χ219,.05 = 30.144
χ2n−1,1−α/2 = χ219,1−.05 = 10.118
(n−1)s2 19∗2.0056
Therefore, LEP= χ2n−1,α/2
= 30.144
(n−1)s2 19∗2.0056
REP = χ2n−1,1−α/2
= 10.118
Chapter 8

Comparing Two Populations

8.1 Confidence Interval of µ1 − µ2

1. The given data is summarizes as follows:

Population I (X) Population II (Y )

Sample Size m = 36 n = 34
Population Mean X = 60.6 Y = 63.7
Population St. Dev σ1 = 11 σ2 = 13

Given level of confidence is 99 percent.

1 − α = .99,qα/2 = .005, zα/2 = z.005 = invN ormal(1 − .005) = 2.5758
q
σ2 σ2 2 2
MOE= zα/2 m1 + n2 = 2.5758 11 36
+ 13
34
= 7.4350
So, LEP= (X − Y ) − E = (60.6 − 63.7) − 7.4350
REP= (X − Y ) − E = (60.6 − 63.7) + 7.4350

2. The given data is summarizes as follows:

Population I (X) Population II (Y )

Sample Size m = 40 n = 36
Population Mean X = 375 Y = 365
Population St. Dev σ1 = 20 σ2 = 10

53
54 CHAPTER 8. COMPARING TWO POPULATIONS

Given level of confidence is 95 percent.

1 − α = .95, α/2q = .025, zα/2 = z.025 = invN ormal(1 − .025) = 1.9600
σ2 σ2
MOE= E = zα/2 m1 + n2
q
2 2
= 1.9600 20
40
+ 10
36
= 7.0062
So, LEP= (X − Y ) − E = (375 − 365) − 7.0062
REP= (X − Y ) − E = (375 − 365) + 7.0062

3. The given data is summarizes as follows:

Population I (X) Population II (Y )
Sample Size m = 18 n = 32
Population Mean X = 11.2 Y = 9.2
Population St. Dev σ1 = 1.5 σ2 = 1
Given level of confidence is 98 percent.
1 − α = .98, α/2q = .01, zα/2 = z.01 = invN ormal(1 − .01) = 2.3263
σ12 σ22
MOE= E = zα/2 m
+ n
q
2 12
= 2.3263 1.5
18
+ 32
= .9195
So, LEP= (X − Y ) − E = (11.2 − 9.2) − .9195
REP= (X − Y ) − E = (11.2 − 9.2) + .9195

4. The given data is summarizes as follows:

Population I (X) Population II (Y )
Sample Size m = 21 n = 48
Population Mean X = 19.9 Y = 17.4
Population St. Dev σ1 = 2.3 σ2 = 2.9
Given level of confidence is 97 percent.
1 − α = .97, α/2q = .015, zα/2 = z.015 = invN ormal(1 − .015) = 2.1701
σ12 σ22
MOE= E = zα/2 m
+ n
q
2 2.92
= 2.1701 2.3
21
+ 48
= 1.4182
So, LEP= (X − Y ) − E = (19.9 − 17.4) − 1.4182
REP= (X − Y ) − E = (19.9 − 17.4) + 1.4182
8.2. WHEN σ1 AND σ2 ARE UNKNOWN 55

8.2 When σ1 and σ2 are unknown

1. Use TI and summarize the data as follows:

Population I (X) Population II (Y )

Sample Size m = 20 n = 21
Sample Mean X = 10.815 Y = 9.0190
Sample St. Dev s1 = 1.4162 s2 = .8072

The pooled estimate of σ is given by

s r
2 2
(m − 1)SX + (n − 1)SX 19 ∗ (1.4162)2 + 20 ∗ (.8072)2
Sp = = = 1.1451
m+n−2 39

Degrees of freedom
df = m + n − 2 = 20 + 21 − 2 = 39
Given level of confidence is 97 percent. Therefore
1 − α = .97, α/2 = .015,
tn−1,α/2 = invT (1 − .015, q
39) = 2.2524 q
MOE= E = tm+n−2,α/2 Sp m1 + n1 = 2.2524 ∗ 1.1451 20 1
+ 1
21
= .8059
So, LEP= (X − Y ) − E = (10.815 − 9.0190) − .8059
REP= (X − Y ) − E = (10.815 − 9.0190) + .8059

2. Summarize the data as follows:

Population I (X) Population II (Y )

Sample Size m = 13 n = 12
Sample Mean X = 19.9 Y = 17.4
Sample St. Dev s1 = 1.8 s2 = 2.2

The pooled estimate of σ is given by

s r
2 2
(m − 1)SX + (n − 1)SX 12 ∗ (1.8)2 + 11 ∗ (2.2)2
Sp = = = 2.0013
m+n−2 23

Degrees of freedom
df = m + n − 2 = 13 + 12 − 2 = 23
56 CHAPTER 8. COMPARING TWO POPULATIONS

Given level of confidence is 98 percent. Therefore

1 − α = .98, α/2 = .01,
tn−1,α/2 = invT (1 − .01, 23)
q = 2.4999 q
1 1 1 1
MOE= E = tm+n−2,α/2 Sp m + n = 2.4999 ∗ 2.0013 13 + 12
= 2.0028
So, LEP= (X − Y ) − E = (19.9 − 17.4) − 2.0028
REP= (X − Y ) − E = (19.9 − 17.4) + 2.0028

3. Summarize the data as follows:

Population I (X) Population II (Y )
Sample Size m = 14 n = 11
Sample Mean X = 3.75 Y = 3.65
Sample St. Dev s1 = 0.22 s2 = 0.18.
The pooled estimate of σ is given by
s r
2 2
(m − 1)SX + (n − 1)SX 13 ∗ (0.22)2 + 10 ∗ (0.18)2
Sp = = = .2036
m+n−2 23
Degrees of freedom
df = m + n − 2 = 14 + 11 − 2 = 23
Given level of confidence is 95 percent. Therefore
1 − α = .95, α/2 = .025,
tn−1,α/2 = invT (1 − .025, q
23) = 2.0687 q
1 1 1 1
MOE= E = tm+n−2,α/2 Sp m + n = 2.0687 ∗ .2036 14 + 11
= .1697
So, LEP= (X − Y ) − E = (3.75 − 3.65) − .1697
REP= (X − Y ) − E = (3.75 − 3.65) + .1697

8.3 Comparing Two Population Proportions

1. Summarize the data as follows:
Population I (X) Population II (Y )
Sample Size m = 227 n = 156
NumberofSuccess X = 106 Y = 48
Sample Prop.ofSuccess X = X
m
= .4670 Y = Yn = .3077
8.3. COMPARING TWO POPULATION PROPORTIONS 57

Given level of confidence is 97 percent. Therefore

1 − α = .97, α/2 = .015,
zα/2 = invN orm(1q − .015) = 2.1701
MOE= E = zα/2 X(1−X) m
+ Y (1−Y
n
)
q
= 2.1701 .4670(1−.4670)
227
+ .3077(1−.3077)
156
= .107678
So, LEP= (X − Y ) − E = (.4670 − .3077) − .107678
REP= (X − Y ) − E = (.4670 − .3077) + .107678

2. Summarize the data as follows:

Population I (X) Population II (Y )

Sample Size m = 210 n = 270
NumberofSuccess X = 97 Y = 88
Sample Prop.ofSuccess X = X
m
= .4619 Y = Yn = .3259

Given level of confidence is 99 percent. Therefore

1 − α = .99, α/2 = .005,
zα/2 = invN orm(1q − .005) = 2.5758
MOE= E = zα/2 X(1−X) m
+ Y (1−Y
n
)
q
= 2.5758 .4619(1−.4619)
210
+ .3259(1−.3259)
270
= .115113
So, LEP= (X − Y ) − E = (.4619 − .3259) − .115113
REP= (X − Y ) − E = (.4619 − .3259) + .115113

3. Summarize the data as follows:

Population I (X) Population II (Y )

Sample Size m = 270 n = 220
NumberofSuccess X = 37 Y = 27
Sample Prop.ofSuccess X = X
m
= .1370 Y = Yn = .1227

Given level of confidence is 95 percent. Therefore

1 − α = .95, α/2 = .025,
zα/2 = invN orm(1q − .025) = 1.9600
X(1−X) Y (1−Y )
MOE= E = zα/2 m
+ n
58 CHAPTER 8. COMPARING TWO POPULATIONS
q
= 1.9600 .1370(1−.1370)
270
+ .1227(1−.1227)
220
= .059681
So, LEP= (X − Y ) − E = (.1370 − .1227) − .059681
REP= (X − Y ) − E = (.1370 − .1227) + .059681
Chapter 9

Testing Hypotheses

9.1 A Significance Test for mean µ when σ is

known
These are also called Z-Tests.

1. The Null and Alternate Hypotheses are


H0 : µ = 51
HA : µ > 51

So, µ0 = 51, The sample size n = 15

The known population standard deviation σ = 5, Observed Sample
mean x =√54 √
z = (x−µσ0 ) n = (54−51)
5
15
= 2.3238
This is a Right Tail Test. So,
p-value pv = P (z < Z) = normalcdf (z, 5)
= normalcdf (2.3238, 5) = .0101

(a) Given Level of Significance is 5 percent. So, α = .05.

We have pv = .0101 < α = .05. So, we reject H0 at 5 percent
level.

59
60 CHAPTER 9. TESTING HYPOTHESES

(b) We have .01 < pv = .0101 < .02. So lowest level of rejection of H0
is 2 percent.
2. The Null and Alternate Hypotheses are

H0 : µ = 112
HA : µ > 112
So, µ0 = 112, The sample size n = 96
The known population standard deviation σ = 17, Observed Sample
mean x =√115 √
z = (x−µσ0 ) n = (115−112)
17
96
= 1.7291
This is a Right Tail Test. So,
p-value pv = P (z < Z) = normalcdf (z, 5)
= normalcdf (1.7291, 5) = .0419

(a) Given Level of Significance is 7 percent. So, α = .07.

We have pv = .0419 < α = .07. So, we reject H0 at 7 percent level
.
(b) We have .04 < pv = .0419 < .05. So lowest level of rejection of H0
is 5 percent.
3. The Null and Alternate Hypotheses are

H0 : µ = 25
HA : µ < 25
So, µ0 = 25, The sample size n = 29
The known population standard deviation σ = 3, Observed Sample
mean x =√23.9 √
z = (x−µσ0 ) n = (23.9−25)
3
29
= −1.9746
This is a Left Tail Test. So,
p-value pv = P (Z < z) = normalcdf (−5, z)
= normalcdf (−5, −1.9746) = .0242.

(a) Given Level of Significance is 6 percent. So, α = .06.

We have pv = .0242 < α = .06. So, we reject H0 at 6 percent level
.
(b) We have .02 < pv = .0242 < .03. So lowest level of rejection of H0
is 3 percent.
9.2. A SIGNIFICANCE TEST FOR MEAN µ WHEN σ IS UNKNOWN61

9.2 A Significance Test for mean µ when σ is

unknown
These are also called T -Tests.

1. The Null and Alternate Hypotheses are


H0 : µ = 23
HA : µ < 23

So, µ0 = 23, The sample size n = 46

Observed Sample mean x = 21.1
Observed √sample standard√
deviation s = 6.,
(x−µ0 ) n (21.1−23) 46
t= s
= 6
= −2.1477
This is a Left Tail Test. So,
p-value pv = P (T < t) = tcdf (−5, t, n − 1)
= tcdf (−5, −2.1477, 45) = .0186.

(a) Given Level of Significance is 6 percent. So, α = .06.

We have pv = .0186 < α = .06. So, we reject H0 at 6 percent level
.
(b) We have .02 < pv = .0186 < .02. So lowest level of rejection of H0
is 2 percent.

2. The Null and Alternate Hypotheses are


H0 : µ = 34
HA : µ > 34

So, µ0 = 34, The sample size n = 26

Observed Sample mean x = 37
Observed √sample standard
√
deviation s = 11,
(x−µ0 ) n (37−34) 26
t= s
= 11
= 1.3906
This is a Right Tail Test. So,
p-value pv = P (t < T ) = tcdf (t, 5, n − 1)
= tcdf (1.3906, 5, 25) = .0883.
62 CHAPTER 9. TESTING HYPOTHESES

(a) Given Level of Significance is 4 percent. So, α = .04.

We have pv = .0883 6< α = .04. So, we will NOT reject H0 at 4
percent level
.
(b) We have .08 < pv = .0883 < .09. So lowest level of rejection of H0
is 9 percent.
3. The Null and Alternate Hypotheses are

H0 : µ = 20
HA : µ > 20
So, µ0 = 20, The sample size n = 31
Observed Sample mean x = 24
Observed √sample standard
√
deviation s = 8,
(x−µ0 ) n (24−20) 31
t= s
= 8
= 2.7839
This is a Right Tail Test. So,
p-value pv = P (t < T ) = tcdf (t, 5, n − 1)
= tcdf (2.7839, 5, 30) = .0046.

(a) Given Level of Significance is 1 percent. So, α = .01.

We have pv = .0046 < α = .01. So, we will reject H0 at 1 percent
level
.
(b) We have .001 < pv = .0046 < .005. So lowest level of rejection of
H0 is .5 percent.
4. The Null and Alternate Hypotheses are

H0 : µ = 10HA : µ > 10
So, µ0 = 10. Use TI. The sample size n = 22
Observed Sample mean x = 14.4091
Observed √sample standard √
deviation s = 7.9502,
(x−µ0 ) n (14.4091−10) 22
t= s
= 7.9502
= 2.6013
This is a Right Tail Test. So,
p-value pv = P (t < T ) = tcdf (t, 5, n − 1)
= tcdf (2.6013, 5, 21) = .0083.
9.2. A SIGNIFICANCE TEST FOR MEAN µ WHEN σ IS UNKNOWN63

(a) Given Level of Significance is 4 percent. So, α = .04.

We have pv = .0083 < α = .04. So, we will reject H0 at 4 percent
level
.
(b) We have .005 < pv = .0083 < .01. So lowest level of rejection of
H0 is 1 percent.
5. The Null and Alternate Hypotheses are

H0 : µ = 33
HA : µ > 33
So, µ0 = 33. The sample size n = 19
Observed Sample mean x = 35
Observed √sample standard√
deviation s = 5.6,
(x−µ0 ) n (35−33) 19
t= s
= 5.6
= 1.5567
This is a Right Tail Test. So,
p-value pv = P (t < T ) = tcdf (t, 5, n − 1)
= tcdf (1.5567, 5, 18) = .0684.

(a) Given Level of Significance is 4 percent. So, α = .04.

We have pv = .0684 6< α = .04. So, we will NOT reject H0 at 4
percent level

(b) We have .06 < pv = .0684 < .07. So lowest level of rejection of H0
is 7 percent.
6. The Null and Alternate Hypotheses are

H0 : µ = 45
HA : µ > 45
So, µ0 = 45. The sample size n = 27
Observed Sample mean x = 42
Observed √sample standard
√
deviation s = 7.5,
(x−µ0 ) n (42−45) 27
t= s
= 7.5
= −2.0785
This is a Left Tail Test. So,
p-value pv = P (T < t) = tcdf (−5, t, n − 1)
= tcdf (−5, −2.0785, 26) = .0238.
64 CHAPTER 9. TESTING HYPOTHESES

(a) Given Level of Significance is 4 percent. So, α = .04.

We have pv = .0238 < α = .04. So, we reject H0 at 4 percent level

(b) We have .02 < pv = .0238 < .03. So lowest level of rejection of H0
is 3 percent.

9.3 Population Proportion

1. The Null and Alternate Hypotheses are

H0 : p = .5
HA : p > .5

So, p0 = .5. The sample size n = 211

Number of success X = 119.
The sample proportion of success X = Xn = √.5640
√
(x−p0 ) n
The Test Statistics z = √ = (.5640−.5)
√
211
.5∗.5
= 1.8593
p0 (1−p0 )
This is a Right Tail Test. So,
p-value pv = P (z < Z) = normalcdf (z, 5)
= normalcdf (1.8593, 5) = .0315.

(a) Given Level of Significance is 4 percent. So, α = .04.

We have pv = .0315 < α = .04. So, we reject H0 at 4 percent level

(b) We have .03 < pv = .0315 < .04. So lowest level of rejection of H0
is 4 percent.

2. The Null and Alternate Hypotheses are


H0 : p = .2
HA : p > .2

So, p0 = .2. The sample size n = 276

Number of success X = 64.
X
The sample proportion of success X = n
= .2319
9.3. POPULATION PROPORTION 65
√ √
(x−p0 ) n (.2319−.2) 276
The Test Statistics z = √ = √
.2∗.8
= 1.3249
p0 (1−p0 )
This is a Right Tail Test. So,
p-value pv = P (z < Z) = normalcdf (z, 5)
= normalcdf (1.3249, 5) = .0926.

(a) Given Level of Significance is 4 percent. So, α = .04.

We have pv = .0926 6< α = .04. So, we will NOT reject H0 at 4
percent level

(b) We have .09 < pv = .0926 < .10. So lowest level of rejection of H0
is 10 percent.

3. The Null and Alternate Hypotheses are


H0 : p = .13
HA : p < .13

So, p0 = .13. The sample size n = 721

Number of success X = 76.
The sample proportion of success X = Xn = .1054√
√
(x−p0 ) n
The Test Statistics z = √ = (.1054−.13)
√
721
= −1.9641
.13∗.87
p0 (1−p0 )
This is a Left Tail Test. So,
p-value pv = P (z < Z) = normalcdf (−5, z)
= normalcdf (−5, −1.9641) = .02476

(a) Given Level of Significance is 4 percent. So, α = .04.

We have pv = .02476 < α = .04. So, we reject H0 at 4 percent level

(b) We have .02 < pv = .02476 < .03. So lowest level of rejection of
H0 is 3 percent.
66 CHAPTER 9. TESTING HYPOTHESES

9.4 Testing Hypotheses on Variance σ 2

1. The Null and Alternate Hypotheses are

H0 : σ 2 = 196
HA : σ 2 > 196

So, σ02 = 196. The sample size n = 27

Sample variance s2 = 324.
2
The Test Statistics Y = (n−1)s
σ02
= 26∗324
196
= 42.9796
This is a Right Tail Test. So,
p-value pv = P (y < Y ) = 1 − P (Y < y) = 1 − χ2 cdf (0, y, n − 1)
= 1 − χ2 cdf (0, 42.9796, 26) = 1 − .9806 = .0194

(a) Given Level of Significance is 5 percent. So, α = .05.

We have pv = .0194 < α = .05. So, we reject H0 at 5 percent level

(b) We have .01 < pv = .0194 < .02. So lowest level of rejection of H0
is 2 percent.
2. The Null and Alternate Hypotheses are

H0 : σ 2 = 5
HA : σ 2 > 5

So, σ02 = 5. The sample size n = 26

Sample variance s2 = 8.8.
2
The Test Statistics Y = (n−1)s
σ02
= 25∗8.8
5
= 44
This is a Right Tail Test. So,
p-value pv = P (y < Y ) = 1 − P (Y < y) = 1 − χ2 cdf (0, y, n − 1)
= 1 − χ2 cdf (0, 44, 25) = 1 − .9892 = .0108

(a) Given Level of Significance is 4 percent. So, α = .04.

We have pv = .0108 < α = .04. So, we reject H0 at 4 percent level

(b) We have .01 < pv = .0108 < .02. So lowest level of rejection of H0
is 2 percent.
9.4. TESTING HYPOTHESES ON VARIANCE σ 2 67

3. The Null and Alternate Hypotheses are


H0 : σ 2 = 20000
HA : σ 2 > 20000

So, σ02 = 20000. The sample size n = 19

Sample variance s2 = 32500.
2
The Test Statistics Y = (n−1)s2
σ0
= 18∗32500
20000
= 29.25
This is a Right Tail Test. So,
p-value pv = P (y < Y ) = 1 − P (Y < y) = 1 − χ2 cdf (0, y, n − 1)
= 1 − χ2 cdf (0, 29.25, 18) = 1 − .9546 = .0454

(a) Given Level of Significance is 4 percent. So, α = .04.

We have pv = .0454 6< α = .04. So, we will NOT reject H0 at 4
percent level

(b) We have .04 < pv = .0454 < .05. So lowest level of rejection of H0
is 5 percent.