ch09 2

Business Statistics, 4e
by Ken Black
Chapter 9
Discrete Distributions
Statistical Inference:
Hypothesis Testing
for Single
Populations
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons.
9-1
Learning Objectives
• Understand the logic of hypothesis testing, and know how to
establish null and alternate hypotheses.
• Understand Type I and Type II errors, and know how to solve
for Type II errors.
• Know how to implement the HTAB system to test hypotheses.
• Test hypotheses about a single population mean when  is
known.
• Test hypotheses about a single population mean when  is
unknown.
• Test hypotheses about a single population proportion.
• Test hypotheses about a single population variance.
9-2
Types of Hypotheses
A hypothesis is a statement about one or more
populations.
•Research Hypothesis
– a statement of what the researcher believes will
be the outcome of an experiment or a study.
•Statistical Hypotheses
– a more formal structure derived from the research
hypothesis.
9-3
Example Research Hypotheses
• Older workers are more loyal to a company
• Companies with more than $1 billion of
assets spend a higher percentage of their
annual budget on advertising than do
companies with less than $1 billion of
assets.
• The price of scrap metal is a good indicator
of the industrial production index simx
months later.
9-4
Elements of a statistical hypothesis test
– Null hypothesis (H 0): Statement regarding the value(s)

of unknown parameter(s). It is the hypothesis to be tested.
– Alternative hypothesis (H 1): Statement contradictory
to the null hypothesis. It is a statement of what we believe
is true if our sample data cause us to reject the null
hypothesis.
– Test statistic - Quantity based on sample data and null
hypothesis used to test between null and alternative
hypotheses
– Rejection region - Values of the test statistic for which
we reject the null in favor of the alternative hypothesis
5
Null and Alternative Hypotheses
• The Null and Alternative Hypotheses are

mutually exclusive. Only one of them can
be true.
• The Null and Alternative Hypotheses are
collectively exhaustive. They are stated to
include all possibilities. (An abbreviated
form of the null hypothesis is often used.)
• The Null Hypothesis is assumed to be true.
• The burden of proof falls on the Alternative
Hypothesis.
9-6
Null and Alternative Hypotheses:
Example
• A manufacturer is filling 40 oz. packages
with flour.
• The company wants the package contents to
average 40 ounces.
Ho :   40 oz
Ha :   40 oz
9-7
One-tailed and Two-tailed Tests
• One-tailed Tests
Ho :   40 Ho : P  0.18
Ha :   40 Ha : P  0.18
• Two-tailed Test
Ho:   12
Ha:   12
9-8
HTAB System to Test Hypotheses
(Hypothesize, Test, Action, Business).
Task 1: Task 3:
HYPOTHESIZE TAKE STATISTICAL ACTION
Task 2: Task 4:
TEST DETERMINING THE
BUSINESS IMPLICATIONS
9-9
Steps in Testing Hypotheses
1. Establish hypotheses: state the null and
alternative hypotheses.
2. Determine the appropriate statistical test and
sampling distribution.
3. Specify the Type I error rate (
4. State the decision rule.
5. Gather sample data.
6. Calculate the value of the test statistic.
7. State the statistical conclusion.
8. Make a managerial decision.
9-10
HTAB Paradigm – Task 1
Task 1: Hypotheses
Step 1. Establish hypotheses:

state the null and alternative
hypotheses.
9-11
Task 2: Test
Step 2. Determine the appropriate statistical test

and sampling distribution.
Step 3. Specify the Type I error rate (
Step 4. State the decision rule.
Step 5. Gather sample data.
Step 6. Calculate the value of the test statistic.
9-12
Task 3: Take Statistical Action
Step 7. State the statistical conclusion.
9-13
Task 4: Determine the business implications
Step 8. Make a managerial decision.
9-14
Rejection and Non Rejection Regions
Rejection Region
Rejection Region
Non Rejection Region

=40 oz
Critical Value Critical Value
9-15
Type I and Type II Errors
• Type I Error
– Rejecting a true null hypothesis
– The probability of committing a Type I error is
called , the level of significance.
• Type II Error
– Failing to reject a false null hypothesis
– The probability of committing a Type II error is
called .
9-16
Decision Table
for Hypothesis Testing
Null True Null False
Fail to Correct Type II error

reject null Decision ()
Reject null Type I error Correct Decision

()
9-17
One-tailed Tests
Ho :   40 Ho :   40
Ha :   40 Ha :   40
Rejection Rejection
Region Region
Non Rejection Region Non Rejection Region

=40 oz =40 oz
Critical Value Critical Value
9-18
Two-tailed Tests
Ho :   40
Ha :   40
Rejection Rejection
Region Region

=12 oz
Critical Values
9-19
CPA Net Income Example
• A survey of CPAs across the United States found that the
average net income for sole proprietor CPAs is $74,914
• Because this survey is now more than ten years old, an
accounting researcher wants to test this figure by taking a
random sample of 112 sole proprietor accountants in the
United States to determine whether the net income figure
changed.
• The researcher could use the eight steps of hypothesis
testing to do so.
• Assume the population standard deviation of net incomes
for sole proprietor CPAs is $14,530
9-20
CPA Net Income Example:
Two-tailed Test (Part 1)
Ho :   $74,914  
.025
.025 2
2
Ha :   $74,914 Rejection
Rejection Region
Region
=0
Zc  196
. Zc  196
.
9-21
Two-tailed Test (Part 2)
If Z  Zc  196
. , reject Ho.
If Z  Zc  196
. , do not reject Ho.
X   78,695  74,914
Z   2.75
 14,530
n 112
Z = 2.75  Zc = 1.96, reject Ho
9-22
Critical Value Method (Part 1)
Ho:   $74,914 Lower


X    Zc
Ha:   $74,914 n
c
14,530
 74,914  196
.
 112
 .025
.025 2  72,223
2
Rejection
Rejection Region Upper
Region

X    Zc
c
n
72,223 77,605
14,530
 74,914  196
.
112
Zc  196
. =0 Zc  196
.  77,605
9-23
Critical Value Method (Part 2)
 
.025 .025
2 2
Rejection
Rejection Region
Region
72,223 77,605
Zc  1.96 =0 Zc  1.96
If X  77,223 or X  77,605, reject Ho.

If 77,223  X  77,605, do not reject Ho.
Since X  78,695  X c
 77,605, reject Ho.
9-24
Problem 9.1
• In an attempt to determine why customer service is
important to managers in the United Kingdom, researchers
surveyed managing directors of manufacturing plants in
Scotland.
• One of the reasons proposed was that customer service is a
means of retaining customers.
• On a scale from 1 to 5, with 1 being low and 5 being high,
the survey respondents rated this reason more highly than
any of the others, with a mean response of 4.30.
• Suppose U.S. researchers believe American manufacturing
managers would not rate this reason as highly and conduct
a hypothesis test to prove their theory.
9-25
• Alpha is set at .05. Data are gathered and the following
results are obtained.
• Use these data and the eight steps of hypothesis testing to
determine whether U.S. managers rate this reason
significantly lower than the 4.30 mean ascertained in the
United Kingdom.
• Assume from previous studies that the population standard
deviation is 0.574.
3 4 5 5 4 5 5 4 4 4 4 4 4 4 4 5 4 4 4 3
4 4 4 3 5 4 4 5 4 4 4 5
9-26
Demonstration Problem 9.1: Z Test
(Part 1)
Ho :   4.30
Ha :   4.30
Rejection
Region
=.05

0
Zc  1645
.
9-27
Demonstration Problem 9.1: Z Test
(Part 2)
Rejection X   4.156  4.30
Region Z   142
.
s 0.574
=.05 n 32
Non Rejection Region Z  1.42  1.645,

Zc  1645
. 0 do not reject H0.
If Z  1645
. , reject H0.
If Z  1.645, do not reject H0.
9-28
Demonstration Problem 9.1: Critical Value
(Part 1)
Ho:   4.30
Rejection
Region
=.05
Ha:   4.30 Non Rejection Region

0
Zc  1645
.
XcZ
s
n
xc  4.133 4.30
0.574
 4.30  ( 1.645)
32
 4.133
9-29
Demonstration Problem 9.1: Critical
Value (Part 2)
Rejection
Region
=.05

0
Zc  1645
.
xc  4.133 4.30
If X  4.133, reject H0.

If X  4.133, do not reject H0.
X  4.156  4.133, do not reject H0.

9-30
Demonstration Problem 9.1: p-Value
Method
Ho:   4.30 Rejection
Region
=.05
Ha:   4.30 Non Rejection Region

0
If p - value <  , reject Ho.
If p - value   , do not reject Ho.
X   4.156  4.30 Since p - value = .0778 >  = .05,

Z   142
. do not reject Ho.
s 0.574
n 32
P ( Z  142
. ) .0778
9-31
Demonstration Problem 9.1: Excel
(Part 1)
9-32
(Part 2)
H0 :  = 4.3
Ha :  < 4.3
3 4 5 5 4 5 5 4
4 4 4 4 4 4 4 5
4 4 4 3 4 4 4 3
5 4 4 5 4 4 4 5
n= =COUNT(A4:H7)
= 0.05
Mean = =AVERAGE(A4:H7)
S= =STDEV(A4:H7)
Std Error = =B12/SQRT(B9)
Z= =(B11-B1)/B13
p-Value =NORMSDIST(B14)
9-33
9-34
Mean 4.156
Variance 0.3296
Observations 32
Hypothesized Mean Difference 4.3
df 31
t Stat -1.416
P(T<=t) one-tail 0.083
t Critical one-tail 1.695
9-35
Two-tailed Test: Small Sample,
 Unknown,  = .05 (Part 1)
Weights in Pounds of a Sample of 20 Plates
22.622.2 23.2 27.4 24.5
27.026.6 28.1 26.9 24.9
26.225.3 23.1 24.2 26.1
25.830.4 28.6 23.5 23.6
X  25.51, S = 2.1933, and n = 20
9-36
 Unknown,  = .05 (part 2)
Ho:   25 Rejection Regions
Ha:   25
 
.025 .025
2
2
df  n  1  19 t  2.093 t c
 2.093
c
Critical Values
9-37
 Unknown,  = .05 (part 3)
Rejection Regions If t  2.093, reject Ho.

If t  2.093, do not reject Ho.
  X   2551
.  250
.
.025 .025
2 t   104
.
2 S 21933
.
n 20
t c
 2.093 t c
 2.093
Critical Values Since t  104

.  2.093, do not reject Ho.
9-38
Machine Plate Example: Excel
(Part 1)
Weights
Mean 25.51
Variance 4.810421
Observations 20
df 19
t Stat 1.0399
P(T<=t) two-tail 0.311437
t Critical two-tail 2.093024
9-39
Machine Plate Example: Excel
(Part 2)
A B C D E
1 H0:  = 25
2 Ha :   25
3
4 22.6 22.2 23.2 27.4 24.5

5 27 26.6 28.1 26.9 24.9
6 26.2 25.3 23.1 24.2 26.1
7 25.8 30.4 28.6 23.5 23.6
8
9 n= =COUNT(A4:E7)
10 = 0.05
11 Mean = =AVERAGE(A4:E7)
12 S= =STDEV(A4:E7)
13 Std Error = =B12/SQRT(B9)
14 t= =(B11-B1)/B13
15 p-Value =TDIST(B14,B9-1,2)
9-40
Demonstration Problem 9.2 (Part 1)
• Figures released by the U.S. Department of Agriculture show that the
average size of farms has increased since 1940.
• In 1940, the mean size of a farm was 174 acres; by 1997, the average size
was 471 acres.
• Between those years, the number of farms decreased but the amount of
tillable land remained relatively constant, so now farms are bigger.
• This trend might be explained, in part, by the inability of small farms to
compete with the prices and costs of large-scale operations and to produce a
level of income necessary to support the farmers’ desired standard of living.
• Suppose an agribusiness researcher believes the average size of farms has
now increased from the 1997 mean figure of 471 acres.
• To test this notion, she randomly sampled 23 farms across the United States
and ascertained the size of each farm from county records.
• The data she gathered follow.
• Use a 5% level of significance to test her hypothesis.
• Assume that number of acres per farm is normally distributed in the
population.
9-41
Size in Acres of 23 Farms
445 489 474 505 553 477 545
463 466 557 502 449 438 500
466 477 557 433 545 511 590
561 560
X  498.78, S = 46.94, and n = 23
9-42
Ho :   471 Rejection Region
Ha :   471
 .05

df  n  1  22
t c
 1717
.
Critical Value
9-43
Rejection Region If t  1717

. , reject Ho.
If t  1717
 .05 X   498.78  471

t   2.84
S 46.94
Non Rejection Region n 23
t c
 1717
.
Critical Value Since t  2.84  1.717, reject Ho.
9-44
Using Excel
Size
Mean 498.7826
Variance 2203.6324
Observations 23
Hypothesized Mean
Difference 471
df 22
t Stat 2.838
P(T<=t) one-tail 0.00478
t Critical one-tail 1.7171
9-45
Estimating the population Proportion
P
p
Z 
PQ
n
 = sample proportion
where: p
P = population proportion
Q = 1 - P
n  P  5, and
nQ  5
9-46
Testing Hypotheses about a Proportion:
Manufacturer Example (Part 1)
• A manufacturer believes exactly 8% of its products contain
at least one minor flaw.
• Suppose a company researcher wants to test this belief.
• The null and alternative
hypotheses are:
Rejection Regions
Ho : P  .08
 
Ha : P  .08 .05 .05
2 2
Z c
 1.645 Z c
 1645
.
Business Statistics, 4e, by Ken Black. © 2003 John Wiley & Sons. Critical Values
9-47
Testing Hypotheses about a Proportion:
Manufacturer Example (Part 2)
Rejection Regions If Z  1645

. , reject Ho.
If Z  1645
33
  p  .165
2
.05 .05 200
2
Non Rejection Region p  P .165.08
Z  1645
. Z  1645
. Z   4.43
c c P Q (.08)(.92)
Critical Values n 200
Since Z  4.43  1645

. , reject Ho.
9-48
Problem 9.3
• A survey of the morning beverage market shows that
the primary breakfast beverage for 17% of Americans
is milk.
• A milk producer in Wisconsin, where milk is
plentiful, believes the figure is higher for Wisconsin.
• To test this idea, she contacts a random sample of 550
Wisconsin residents and asks which primary beverage
they consumed for breakfast that day.
• Suppose 115 replied that milk was the primary
beverage.
• Using a level of significance of .05, test the idea that
the milk figure is higher for Wisconsin.
9-49
Ho: P .17 Rejection Region
Ha: P .17  .05

Z c
 1645
.
Critical Value
9-50
If Z  1645
. , reject Ho.
Rejection Region If Z  1645
115
 .05 p  .209
550
p  P .209 .17
Non Rejection Region Z   2.44
P Q (.17)(.83)
Z c
 1645
.
n 550
Critical Value
Since Z = 2.44  1645
. , reject Ho.
9-51
Testing Hypotheses about a Variance
• At times a researcher needs to test hypotheses about

a population variance.
• For example, in the area of statistical quality
control, manufacturers try to produce equipment
and parts that are consistent in measurement.
• The procedure for testing hypotheses about a
population variance is similar to the techniques
presented in Chapter 8 for estimating a population
variance from the sample variance
9-52
Testing Hypotheses about a Variance
53
Problem 9.4
• A small business has 37 employees. Because of the
uncertain demand for its product, the company usually
pays overtime on any given week.
• The company assumed that about 50 total hours of
overtime per week is required and that the variance on this
figure is about 25.
• Company officials want to know whether the variance of
overtime hours has changed.
• Given here is a sample of 16 weeks of overtime data (in
hours per week).
• Assume hours of overtime are normally distributed.
• Use these data to test the null hypothesis that the variance
of overtime data is 25.
9-54
Hypothesis Test for 2:
Ho: 2
 25
H :
2
a  25
df = 15
.05
.95
.05
0
7.26094 24.9958
9-55
Hypothesis Test for 2:
 n  1 S 2 15 28.1

2
   16.86

2
25
 
2 2
Since  16.86  .05,15
 24.9958,
do not reject Ho.
9-56

ch09 2

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

ch09 2

Uploaded by

Copyright:

Available Formats

Business Statistics, 4e

– Null hypothesis (H 0): Statement regarding the value(s)

• The Null and Alternative Hypotheses are

Step 1. Establish hypotheses:

Step 2. Determine the appropriate statistical test

Step 7. State the statistical conclusion.

Step 8. Make a managerial decision.

Non Rejection Region

Critical Value Critical Value

Null True Null False

Fail to Correct Type II error

Reject null Type I error Correct Decision

Non Rejection Region Non Rejection Region

Critical Value Critical Value

Non Rejection Region

Ho:   $74,914 Lower

Zc  1.96 =0 Zc  1.96

If X  77,223 or X  77,605, reject Ho.

Non Rejection Region

Non Rejection Region Z  1.42  1.645,

Ha:   4.30 Non Rejection Region

Non Rejection Region

If X  4.133, reject H0.

X  4.156  4.133, do not reject H0.

Ha:   4.30 Non Rejection Region

X   4.156  4.30 Since p - value = .0778 >  = .05,

X  25.51, S = 2.1933, and n = 20

Ho:   25 Rejection Regions

Rejection Regions If t  2.093, reject Ho.

Critical Values Since t  104

P(T<=t) two-tail 0.311437

t Critical two-tail 2.093024

4 22.6 22.2 23.2 27.4 24.5

X  498.78, S = 46.94, and n = 23

Ho :   471 Rejection Region

Non Rejection Region

Rejection Region If t  1717

 .05 X   498.78  471

Critical Value Since t  2.84  1.717, reject Ho.

Rejection Regions If Z  1645

Since Z  4.43  1645

Ho: P .17 Rejection Region

Ha: P .17  .05

Non Rejection Region

• At times a researcher needs to test hypotheses about

You might also like