BT10403

Statistik Perniagaan dan Ekonomi

(Statistics for Business and
Economics)
Week 14a, Semester II, 2016/2017
School of Business & Economics,
Universiti Malaysia Sabah
Dr. Qaiser Munir

1
Business Statistics: Communicating with Numbers
 Chapter 10 Learning Objectives (LOs)
LO 10.1: Make inferences about the difference
between two population means
based on independent sampling.
LO 10.2: Make inferences about the mean
difference based on matched-pairs
sampling.

10-3
Comparing Two populations
Some Examples
1. Is there a difference in the mean value of
residential real estate sold by male agents and
female agents in south Florida?

2. Is there a difference in the mean number of

defects produced during the day and the
afternoon shifts at Kimble Products?

3. Is there a difference in the mean number of days

absent between young workers (under 21 years
of age) and older workers (more than 60 years
of age) in the fast-food industry?

11-4
10-4
10.1 Inference Concerning the Difference
Between Two Means
LO 10.1 Make inferences about the difference between two population means
based on independent sampling.

Independent Random Samples

Two (or more) random samples are considered
independent if the process that generates one
sample is completely separate from the process
that generates the other sample.
The samples are clearly delineated.
m1 is the mean of the first population.
m2 is the mean of the second population.

10-5
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Confidence Interval for m1 m2
X1 X 2 is a point estimator of m1 m2.
The values of the sample means x1 and x 2 are computed
from two independent random samples with n1 and n2
observations, respectively.
Sampling distribution of X1 X 2 is assumed to be
normally distributed.
A linear combination of normally distributed random
variables is also normally distributed.
If underlying distribution is not normal, then by the central
limit theorem, the sampling distribution of X1 X 2 is
approximately normal only if both n1 > 30 and n2 > 30.

10-6
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Consider these scenarios:
1. If we know s21 and s22, then use the
z distribution.
2. If we do not know s21 and s22 but can assume
that they are equal, then use the tdf distribution
with a pooled estimate of the variance s2p.
3. If we do not know s21 and s22 but cannot assume
that they are equal, then use the tdf distribution
with s21 and s22.

10-7
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Test a hypothesis that two independent population means with known
population standard deviations are equal.

1. If s21 and s22 are known, a 100(1 a)%

confidence interval of the difference between
two population means m1 m2 is given by

s 2
s 2

x1 x2 za /2 1
2
n1 n2

10-8
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

2. If s21 and s22 are unknown but assumed equal, a
100(1 a)% confidence interval of the difference
between two population means m1 m2 is given by
1 1
x1 x2 ta /2,df s
2
p
n1 n2

where sp2 1
n 1 s1
2
n2 1 s 2
2
and s12 and s22 are
n1 n2 2
the corresponding sample variances and
df n1 n2 2

10-9
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

3. If s21 and s22 are unknown but cannot be assumed
to be equal, a 100(1 a)% confidence interval of
the difference between two population means
m1 m2 is given by
s12 s22
x1 x2 ta /2,df
n1 n2

s
2
2
1 n1 s n22
2
where df
s n
1 s n2 n 1
2 2
2 2
1 n1 1 2 2

10-10
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Hypothesis Test for m1 m2
When conducting hypothesis tests concerning
m1 m2 , the competing hypotheses will take one
of the following forms:

where d0 is the hypothesized difference between

m1 and m2. in most cases it is zero.

10-11
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Test Statistic for Testing m1 m2 when the
sampling distribution for X1 X 2 is normal.
1. If s21 and s22 are known, then the test statistic is
assumed to follow the z distribution and its value
is calculated as

z
x1 x2 d0
s 12 s 22

n1 n2

10-12
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Test Statistic for Testing m1 m2 when the
sampling distribution for X1 X 2 is normal.
2. If s21 and s22 are unknown but assumed equal,
then the test statistic is assumed to follow the
tdf distribution and its value is calculated as

tdf
x1 x2 d0

s2 1
n 1 s1
2
n2 1 s 2
2
where p
1 1 n1 n2 2
sp
2

n1 n2 and df n1 n2 2

10-13
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Test Statistic for Testing m1 m2 when the sampling
distribution for X1 X 2 is normal.
3. If s21 and s22 are unknown and cannot be
assumed equal, then the x1 x2 d0
test statistic is assumed to tdf
follow the tdf distribution and s 2
s 2


1 2

its value is calculated as: n1 n2

s
2
2
1 n1 s 2
2 n2
where df
s n
1 s n 1
2 2
2 2
1 n1 1 2 n2 2

is rounded down to the nearest integer.

10-14
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Example 1: A consumer advocate analyzes the
nicotine content in two brands of cigarettes. A
sample of 20 cigarettes of Brand A and 25
cigarettes of Brand B yielded the following data.
Sample average are 1.68 and 1.95.
Sample SD are 0.22mg and 0.24mg.

Using this information, we will construct a 95%

confidence interval and perform a hypothesis test
about the difference between the two means.

10-15
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

1

1 2
x x t s 1 2 a /2,df p
n1 n2

Example 1: A 95% confidence interval and

hypothesis test about m1 m2 are as follows.
Let m1 represent the mean of Brand A and m2

represent the mean of Brand B.

Here, the population variances are unknown
and assumed equal, so start by calculating the
pooled variance s2p s n 1 s n 1 s
2 1
2
1 2
2
2

n1 n2 2
p

20 1 0.22 25 1 0.24
2 2

sp2 0.0535
20 25 2
and df df 20 25 2 43
10-16
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Example 1: A 95% confidence interval and

hypothesis test about m1 m2 are as follows.
For a = 0.05 and a/2 = 0.025, from the t table, we
find t0.025,43 = 2.017.
Thus, a 95% confidence interval about m1 m2 is:
1 1
0.27 2.017 0.0535 0.27 0.14 or 0.41, 0.13
20 25

10-17
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Example 1: A 95% confidence interval and
hypothesis test about m1 m2.
We want to determine if the average nicotine levels
differ between the two brands, or m1 m2.
The two-tailed hypotheses are H0: m1 = m2
H A : m1 m2
The hypothesized difference of 0 is not included in the
95% confidence interval:
0.27 0.14 or [0.41, 0.13]
Reject H0; the average nicotine levels between the
two brands differ at the 5% significance level.

10-18
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Example 2: Hypothesis test about m1 m2.
Claim: Average weekly food expenditure of
households in City 1 is more than that of households
in City 2.
A survey of 35 households in City 1 and 30
households in City 2 to obtain the following data.
Let m1 be the mean weekly
expenditure for City 1 and
m2 be the mean weekly
expenditure for City 2.

10-19
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Example 2: Hypothesis test about m1 m2.
The economist wishes to determine if the mean
weekly food expenditure in City 1 is more than that of
City 2, or m1 > m2.
The hypotheses for this right-tailed test are:
H0: m1 < m2, HA: m1 > m2
Since the population standard deviations are known,
we assume the
z
164 159 0
1.85
Z test statistic.
12.50 9.25
2 2

35 30

10-20
 10.1 Inference Concerning the Difference
LO 10.1

Between Two Means

Example 2: Hypothesis test about m1 m2.
The p-value of the right-tailed test is computed as
p-value = P(Z > 1.85) = 1 0.9678 = 0.0322.
Since the p-value of 0.0322 < a = 0.05 the
significance level) we reject the null hypothesis.
Therefore, at the 5% significance level, the
economist concludes that average weekly food
expenditure in City 1 is more than that of City 2.

10-21
10.2 Inference Concerning Mean Differences
LO 10.2 Make inferences about the mean difference based on matched-pairs
sampling.

Matched-Pairs Sampling
Parameter of interest is the mean difference D
where D = X1 X2 , and the random variables
X1 and X2 are matched in a pair.
Both X1 and X2 are normally distributed or
n > 30.
For example, assess the benefits of a new
medical treatment by evaluating the same
patients before (X1) and after (X2) the treatment.

10-22
LO 10.2 10.2 Inference Concerning Mean Differences
Recognizing a Matched-Pairs Experiment
1. Before and after studies characterized by a
measurement, some type of intervention, and
another measurement, all on the same subject.
Example: Measuring the weight of clients
before and after a diet plan.
2. A pairing of observations, where it is not on the
same subject that gets sampled twice.
Example: Matching 20 adjacent plots of land
using a nonorganic fertilizer on one half of the
plot and an organic fertilizer on the other.

10-23
LO 10.2 10.2 Inference Concerning Mean Differences
Confidence Interval for mD
A 100(1 a)% confidence interval of the mean
difference (mD) is given by

d ta /2,df sD n

where d and sD are the mean and the standard

deviation, respectively, of the n sample
differences, and df = n 1.

10-24
LO 10.2 10.2 Inference Concerning Mean Differences
Hypothesis Test for mD
When conducting hypothesis tests concerning
mD, the competing hypotheses will take one
of the following forms:

where d0 typically is equal to 0.

10-25
LO 10.2 10.2 Inference Concerning Mean Differences
Test Statistic for Hypothesis Tests About mD
The test statistic for hypothesis tests about mD
is assumed to follow the tdf distribution with
df = n 1, and its value is
d d0
tdf
sD n
where d and sD are the mean and standard
deviation, respectively, of the n sample
differences, and d0 is a given hypothesized mean
difference.

10-26
LO 10.2 10.2 Inference Concerning Mean Differences
Example: Confidence interval and hypothesis
test about mD.
Interested in improving productivity at a plant by
changing the layout of the workstation, a manager
measures the productivity of 10 workers before
the change and again after the change.
The hypotheses are: H0: mD = 0, HA: mD 0
Given the following sample statistics, construct a
95% confidence interval for the mean difference.

d 8.5, sp 11.38, n 10

10-27
LO 10.2 10.2 Inference Concerning Mean Differences
Example: Confidence interval and hypothesis
test about mD.
df = 10 1 = 9 and a = 0.05.
From the t table, ta/2,df = t0.025,9 = 2.262 and a 95%
confidence interval for the mean difference is

8.5 2.262 11.38
10 8.5 8.14 or 0.36,16.64

Reject H0: mD = 0 since the hypothesized mean

difference of 0 is not included in the interval.
Conclude that there has been a change in
productivity due to the different layout.

10-28
Now its your turn!

10-29
Comparing Population Means with Unknown Population
Standard Deviations (the Pooled t-test)
X1 X 2
(n1 1) s (n2 1) s
2 2 t
s 2p 1 2
2 1 1
n1 n2 2 s p
n1 n2

Owens Lawn Care, Inc., manufactures and

assembles lawnmowers. Two different
procedures have been proposed for mounting
the engine on the frame of the lawnmower.

Five employees were timed using the Welles

method and six using the Atkins method. The
results, in minutes, are shown on the right.

Is there a difference in the mean mounting

times between the two methods? Use the 0.10
significance level.

11-30
10-30
 Conduct a hypothesis test that two independent population means are equal,
assuming equal but unknown population standard deviations.

Comparing Population Means with Equal but Unknown

Population Standard Deviations (the Pooled t-test)
Use t distribution if:
One or both of the samples have less than 30
observations, and
The population standard deviations are unknown.

Assumptions:
Both populations must follow the normal distribution.
The populations must have equal standard
deviations.
The samples are from independent populations.
11-31
10-31
Small Sample Test of Means continued

Finding the value of the test

statistic requires two
( n 1) s 2
( n 1) s 2
steps. s 2p 1 1 2 2
n1 n2 2
1. Pool the sample standard
deviations.

X1 X 2
2. Use the pooled standard t
deviation in the formula. 2 1 1
s p
n1 n2

11-32
10-32
Comparing Population Means with Unknown Population Standard
Deviations (the Pooled t-test) Example

Step 1: State the null and alternate hypotheses.

(Keyword: Is there a difference)

H0: 1 = 2
H1: 1 2

Step 2: State the level of significance. The 0.10 significance level is

stated in the problem.

Step 3: Find the appropriate test statistic.

Because the population standard deviations are not known but are
assumed to be equal, we use the pooled t-test.

11-33
10-33
Comparing Population Means with Unknown Population
Standard Deviations (the Pooled t-test) Example

Step 4: State the decision rule.

Reject H0 if computed t > critical t or

if computed t < - critical t
(alpha 0.10, d.f. 9)

11-34
10-34
Students t distribution Table

11-35
10-35
Comparing Population Means with Unknown Population
Standard Deviations (the Pooled t-test) Example
Step 5: Compute the value of t and make a decision
(a) Calculate the sample standard deviations.

11-36
10-36
Comparing Population Means with Unknown Population
Standard Deviations (the Pooled t-test) Example

Step 5: Compute the value of t and make a decision

The decision is not to reject the

null hypothesis, because
0.662 falls in the region
between 1.833 and 1.833.

We conclude that there is no

difference in the mean times to
mount the engine on the frame
0.662
using the two methods.

11-37
10-37
 Hypothesis Testing Involving Dependent Samples Example
Matched-Pairs Sampling

Nickel Savings and Loan wishes to compare the two companies it uses to
appraise the value of residential homes. A sample of 10 residential
properties are appraised by both companies. The results, reported in
$000, are shown in the table.
At the .05 significance level, can we conclude there is a difference in the
mean appraised values of the homes?

11-38
10-38
Hypothesis Testing Involving Dependent Samples

t-statistic when the samples are dependent:

d
t
sd / n
Where:
d is the mean of the differences
sd is the standard deviation of the differences
n is the number of pairs (differences)

11-39
 LO 11-5
Hypothesis Testing Involving Paired Observations
Example

Step 1: State the null and alternate hypotheses.

H0: md = 0
H1: md 0

Step 2: State the level of significance.

The .05 significance level is stated in the problem.

Step 3: Find the appropriate test statistic using the t-test.

11-40
Hypothesis Testing Involving Paired
Observations Example
Step 4: State the decision rule.
Reject H0 if computed t > critical t or
computed t < critical t

11-41
Hypothesis Testing Involving Paired
Observations Example
Step 5: Compute the value of t and make a decision.

Conclusion:
Reject the null hypothesis
of no difference since
computed t is greater than
the higher critical t value.

Interpretation:
There is a difference in the
mean appraised values of
the homes by the two
companies.

11-42
Comparing Two Population Means Example
Test a hypothesis that two independent population means with
known population standard deviations are equal.
The U-Scan facility was recently installed at the Byrne Road Food-Town
location. The store manager would like to know if the mean checkout time
using the standard checkout method is longer than using the U-Scan. She
gathered the following sample information on service time. Use 0.01
significance level.

Use if s 1 and s 2 are known

X1 X 2
z
s 12 s 22

n1 n2
11-43
10-43
EXAMPLE 1 continued

Step 1: State the null and alternate hypotheses.

(keyword: longer than)
H0: S U
H1: S > U

Step 2: Select the level of significance.

The .01 significance level is stated in the problem.

Step 3: Determine the appropriate test statistic.

Because both population standard deviations are known, we can
use z distribution as the test statistic.

10-44
Example 1 continued
Step 4: Formulate a decision rule.
Reject H0 if computed z > critical z

11-45
10-45
Finding the z Value for a Right-Tailed Test
E = 0.03 of true proportion
Given a Significance Level of95%
0.01Confidence Level

11-46
10-46
Example 1 continued

Step 5: Compute the value of z and make a decision.

Xs Xu
z
s s2 s u2

ns nu
The computed value of 3.13 is larger
5.5 5.3 than the critical value of 2.33.

0.40 2 0.30 2 Conclusion: Reject the null

hypothesis.
50 100
0.2 The U-Scan method is faster.
3.13
0.064 11-47
10-47
THANK YOU!

10-48