Data Analysis for Managers

Unit III (Part 2):

Testing of Statistical Hypotheses
Rajashree Kamath Ph.D. (Statistics),
Assistant Professor (Business Analytics),
Coordinator - AcadX (Kengeri Campus),
Coordinator - CSR Karma Club (Kengeri Campus) – Sustainability Cell,
School of Business and Management,
CHRIST (Deemed to be University) - BKC, Bangalore 560074.
Ph.: +918040129879 (O), Cell: +919448067196.
MISSION VISION CORE VALUES
CHRIST is a nurturing ground for an individual’s Excellence and Service Faith in God | Moral Uprightness
holistic development to make effective contribution to Love of Fellow Beings
the society in a dynamic environment Social Responsibility | Pursuit of Excellence
 CHRIST
Deemed to be University

Introduction

● Make a tentative assumption about a population parameter, called the

null hypothesis denoted by H0. For e.g., H0: p = 0.5
● Define another hypothesis, called the alternative hypothesis, which
is the opposite of what is stated in the null hypothesis. The alternative
hypothesis is denoted by Ha. For e.g., Ha: p ≠ 0.5
● One-Sided Hypothesis (<, >)
● Two-Sided Hypothesis (≠)

Excellence and Service

 CHRIST
Deemed to be University

Example Scenarios

● Nielsen reported that young men in the United States watch 56.2
minutes of prime-time TV daily (The Wall Street Journal Europe,
November 18, 2003). A researcher believes that young men in
Germany spend more time watching prime-time TV. A sample of
German young men will be selected by the researcher and the time
they spend watching TV in one day will be recorded. What null and
alternative hypotheses will you use to test the researcher's belief?
H0:  ≤ 56.2
Ha:  > 56.2

● The label on a 3-quart container of orange juice states that the orange
juice contains an average of 1 gram of fat or less.
H0:  ≤ 1
Ha:  > 1
Excellence and Service
 CHRIST
Deemed to be University

Example Scenarios (Contd.)

● Carpetland salespersons average $8000 per week in sales. Steve

Contois, the firm’s vice president, proposes a compensation plan with
new selling incentives. Steve hopes that the results of a trial selling
period will enable him to conclude that the compensation plan
increases the average sales per salesperson.
H0:  ≤ 8000 vs. Ha:  > 8000

● Suppose a new production method will be implemented if a

hypothesis test supports the conclusion that the new method reduces
the mean operating cost per hour.
H0:  ≥ 0
Ha: mu < mu0

Excellence and Service

 CHRIST
Deemed to be University

Type I and Type II Errors

Population H0 True Ha True (H0
Condition False)

Conclusion
Accept H0 Correct (1 - 𝛼) Type II Error (β)
Reject H0 (Accept Type I Error (α) Correct (1 – β)
Ha) Power of the test
● The probability of rejecting the null hypothesis when it is true as an
equality is called the level of significance, denoted by 𝛼. P[Reject H0
| H0 is true] = 𝛼
● The probability of accepting the null hypothesis when it is false is
denoted by 𝛽.
● The probability rejecting the null hypothesis when it is false is called
as the Power of the test, given by 1 - 𝛽.
● Power is calculated at the value given by the alternative hypothesis.
Excellence and Service
 CHRIST
Deemed to be University

Test for Population Mean, 𝜎 Known

● Two-Tailed Test: H0: 𝜇 = 𝜇0, Ha: 𝜇 ≠ 𝜇0
● Lower Tail Test:H0: 𝜇 ≥ 𝜇0, Ha: 𝜇 < 𝜇0
● Upper Tail Test: H0: 𝜇 ≤ 𝜇0, Ha: 𝜇 > 𝜇0

● Based on sampling distribution of X – Normal (Z) with mean 𝜇0 and

s.d. 𝜎.

● Criteria for Rejection for Two-Tailed Test:

○Confidence Interval Approach: Reject H0 if 𝜇0 is outside the (1 -
𝛼)% confidence interval.
○ Critical Value Approach: T.S. (Test Statistic) = ,
○Critical value = z𝛼/2; P[Z > z𝛼/2] = 𝛼/2
○Reject H0 if T.S < -z𝛼/2 or T.S > z𝛼/2
○ p-value Approach: p-value = 2 x P[Z < T.S.] if T.S. < 0
= 2 x P[Z > T.S]if T.S. > 0 and Service
Excellence
 CHRIST
Deemed to be University

One-Tailed Tests

● Criteria for Rejection for Lower Tail Test (H0: 𝜇 ≥ 𝜇0, Ha: 𝜇 < 𝜇0):
○ Critical Value Approach:
Critical value = z𝛼; P[Z > z𝛼] = 𝛼
Reject H0 if T.S. < -z𝛼
○ p-value Approach: p-value = P[Z < T.S.]
Reject H0 if p-value < 𝛼

● Criteria for Rejection for Upper Tail Test (H0: 𝜇 ≤ 𝜇0, Ha: 𝜇 > 𝜇0):
○ Critical Value Approach:
Critical value = z𝛼; P[Z > z𝛼] = 𝛼
Reject H0 if T.S > z𝛼
○ p-value Approach: p-value = P[Z > T.S.]
Reject H0 if p-value < 𝛼 0 Z𝛼
TS
Excellence and Service
 CHRIST
Deemed to be University

Exercise 1

● Individuals filing federal income tax returns prior to March 31

received an average refund of $1056. Consider the population of
“last-minute” filers who mail their tax return during the last five days
of the income tax period (typically April 10 to April 15).
a. A researcher suggests that a reason individuals wait until the last five
days is that, on an average, they will need to claim lower refunds
than the early filers. Develop appropriate hypotheses to test this.
b. For a sample of 400 individuals who filed a tax return between April
10 and 15, the sample mean refund was $910. Based on prior
experience a population standard deviation of $1,600 may be
assumed. What is the p-value?
c. At α = .05, what is your conclusion?
d. Repeat the preceding hypothesis test using the critical value approach

Excellence and Service

 CHRIST
Deemed to be University

● b) Given, mu0 = 1056, xbar = 910, n = 400, sigma = 1600

To test H0: mu >= 1056 versus Ha: mu < 1056 at alpha = 0.05 (5% level
of significance).

Reject H0 if TS = < -z𝛼

TS = (910 – 1056)/(1600/) = -1.825

The critical value, z𝛼 = 1.645

Since -1.825 < -1.645, the criterion for rejection is satisfied. Hence, we
reject H0 at the 5% level of significance. This means, the average refund
of last time filers is indeed less than 1056, and the researcher’s claim is
true with a 5% chance of error in judgement.
Excellence and Service
 CHRIST
Deemed to be University

Exercise 2
● Fowle Marketing Research, Inc., bases charges to a client on the assumption
that telephone surveys can be completed in a mean time of 15 minutes or
less. If a longer mean survey time is necessary, a premium rate is charged. A
sample of 35 surveys provided the survey times shown in the file named
Fowle. Based upon past studies, the population standard deviation is
assumed known with σ = 4 minutes. Is the premium rate justified?
● a. Formulate the null and alternative hypotheses for this application.
H0: mu <= 15 Ha: mu > 15
● b. Compute the value of the test statistic.
n = 35, σ = 4, xbar = 17
TS = (xbar – mu0)/[sigma/sqrt(n)] = 2.95
● c. What is the p-value?
For an upper tail test, p-value = P[Z > TS] = P[Z > 2.95] = 1 - 0.9984 = 0.0016
● d. At α = .01, what is your conclusion?
Since the p-value = 0.0016 < 0.01, we reject H0 at the 1% level of significance.
That means, the mean survey time is more than 15 min with a 1% chance of error in judgement. So,
the premium rate is justified.
● AndersonData\Ch 09 Hypothesis Tests\Fowle.xlsx
● Ans: The mean of the data in the Excel file is 17. The rest is solved in class.
Excellence and Service
 CHRIST
Deemed to be University

Test for Population Mean, 𝜎 Unknown

● Two-Tailed Test: H0: 𝜇 = 𝜇0, Ha: 𝜇 ≠ 𝜇0

● Lower Tail Test:H0: 𝜇 ≥ 𝜇0, Ha: 𝜇 < 𝜇0
● Upper Tail Test: H0: 𝜇 ≤ 𝜇0, Ha: 𝜇 > 𝜇0

● Criteria for Rejection:

○ Confidence Interval Approach

○ Critical Value Approach
○ p-value Approach

○ Use t with (n – 1) degrees of freedom instead of z (Pg. 977 of e-

book).
Excellence and Service
 CHRIST
Deemed to be University

Exercise 3

● The Employment and Training Administration reported that the U.S.

mean unemployment insurance benefit was $238 per week (The
World Almanac, 2003). A researcher in the state of Virginia
anticipated that sample data would show evidence that the mean
weekly unemployment insurance benefit in Virginia was below the
national average.
a. Develop appropriate hypotheses to test the researcher's claim.
b. For a sample of 100 individuals, the sample mean weekly
unemployment insurance benefit was $231 with a sample standard
deviation of $80. What is the p-value?
c. At α = .05, what is your conclusion?
d. Repeat the preceding hypothesis test using the critical value
approach.

Excellence and Service

 CHRIST
Deemed to be University

Test for Population Proportion

● Two-Tailed Test: H0: p = p0, Ha: p ≠ p0

● Lower Tail Test:H0: p ≥ p0, Ha: p < p0
● Upper Tail Test: H0: p ≤ p0, Ha: p > p0

● Criteria for Rejection:

○ Confidence Interval Approach

○ Critical Value Approach T.S. = (pbar – p0)/
○ p-value Approach
○ Based on sampling distribution of pbar - Normal (Z) with mean p0
and s.d. )

Excellence and Service

 CHRIST
Deemed to be University

Exercise 4

● A study found that, in 2005, 12.5% of U.S. workers belonged to

unions (The Wall Street Journal, January 21, 2006). Suppose a sample
of 400 U.S. workers is collected in 2006 to determine whether union
efforts to organize have increased union membership.
a. Formulate the hypotheses that can be used to determine whether
union membership increased in 2006.
b. If the sample results show that 52 of the workers belonged to
unions, what is the p-value for your hypothesis test?
c. At α = .05, what is your conclusion?

Excellence and Service

 CHRIST
Deemed to be University

Exercise 5

● Speaking to a group of analysts in January 2006, a brokerage firm

executive claimed that at least 70% of investors are currently
confident of meeting their investment objectives. A UBS Investor
Optimism Survey, conducted over the period January 2 to January 15,
found that 67% of investors were confident of meeting their
investment objectives (CNBC, January 20, 2006).
a. Formulate the hypotheses that can be used to test the validity of
the brokerage firm executive’s claim.
b. Assume the UBS Investor Optimism Survey collected information
from 300 investors.
c. What is the p-value for the hypothesis test?
d. At α = .05, should the executive’s claim be rejected?

Excellence and Service

 CHRIST
Deemed to be University

Two Populations: Matched (Paired) Samples

● The same sample units are observed "Before" and "After" a given
process happens. For e.g., weight-loss program. People of certain
weight undergo a weight-loss program and their weights are recorded
before and after the program. The difference in weight (After minus
Before) is a random sample which can be treated as a one sample
scenario.
● Although the population characteristics have changed after the
process, which means we are testing for two populations, this is
essentially like observing the difference in values before and after the
process. Excellence and Service
 CHRIST
Deemed to be University

Exercise 6

● A market research firm used a sample of individuals to rate the

purchase potential of a particular product before and after the
individuals saw a new television commercial about the product. The
purchase potential ratings were based on a 0 to 10 scale, with higher
values indicating a higher purchase potential. The null hypothesis
stated that the mean rating “after” would be less than or equal to the
mean rating “before.” Rejection of this hypothesis would show that
the commercial improved the mean purchase potential rating. Use the
following data to test the hypothesis and comment on the value of the
commercial.

● After: 6, 6, 7, 4, 3, 9, 7, 6
● Before: 5, 4, 7, 3, 5, 8, 5, 6

Excellence and Service

 CHRIST

Two Population Means Deemed to be University

● Two-Tailed Test: H0: 𝜇1 = 𝜇2, Ha: 𝜇1 ≠ 𝜇2

● Lower Tail Test: H0: 𝜇1 ≥ 𝜇2, Ha: 𝜇1 < 𝜇2
● Upper Tail Test: H0: 𝜇1 ≤ 𝜇2, Ha: 𝜇1 > 𝜇2
● Known Variances (z-Test) (Excel Data Analysis Add-in ‘z-Test: Two-Sample for
Means’):
● T.S. =
● Unknown Variances (t-Test):
○ Equal (Excel Data Analysis Add-in ‘t-Test: Two-Sample Assuming Equal
Variances’):
○ T.S. = ;
○ Unequal (Excel Data Analysis Add-in ‘t-Test: Two-Sample Assuming Unequal
Variances’):
○ T.S. = ; d.f. =

Excellence and Service

 CHRIST
Deemed to be University

Exercise 7

● Suppose that you are responsible for making arrangements for a

business convention. Because of budget cuts due to the recent
recession, you have been charged with choosing a city for the
convention that has the least expensive hotel rooms. You have
narrowed your choices to Atlanta and Houston. The file named Hotel
contains samples of prices for rooms in Atlanta and Houston that are
consistent with the results reported by Smith Travel Research
(SmartMoney, March 2009). Because considerable historical data on
the prices of rooms in both cities are available, the population
standard deviations for the prices can be assumed to be $20 in Atlanta
and $25 in Houston. Based on the sample data, can you conclude that
the mean price of a hotel room in Atlanta is lower than one in
Houston?
● AndersonData\Ch 10 Two Populations\Hotel.xlsx
Excellence and Service
 CHRIST
Deemed to be University

● Given sd are known, sigma1 = 20, sigma2 = 25 and we are testing

H0: 𝜇1 ≥ 𝜇2, Ha: 𝜇1 < 𝜇2
To test this, the rejection criterion is

Reject H0 if TS = < -z𝛼

(If , the LHS will be positive. Since the RHS is always negative, this
implies that, if , we straightaway accept H0.)

Excellence and Service

 CHRIST
Deemed to be University

Exercise 8

● FedEx and United Parcel Service (UPS) are the world’s two leading
cargo carriers by volume and revenue (The Wall Street Journal,
January 27, 2004). According to the Airports Council International,
the Memphis International Airport (FedEx) and the Louisville
International Airport (UPS) are 2 of the 10 largest cargo airports in the
world. The following random samples show the tons of cargo per day
handled by these airports. Data are in thousands of tons:
Memphis: 9.1, 8.3, 15.1, 9.1, 8.8, 6, 10, 5.8, 7.5, 12.1, 10.5, 9.3
Louisville: 4.7, 2.2, 5, 4.1, 4.2, 2.6, 3.3, 3.4, 5.5, 7
a. Formulate hypothesis to test whether the average amount of cargo
handled by the two airports are the same.
b. What is the p-value?
c. Use 𝛼 = .05. What is your conclusion?
d. What is your conclusion based on the critical value approach?
Excellence and Service