Ch 10

Example (1)
You are a financial analyst for a brokerage firm. Is there a difference in dividend
yield between stocks listed on the NYSE & NASDAQ? You collect the following
data:
NYSE: 𝑛1 = 21 , 𝑋̅1 = 3.27 , 𝑆1 = 1.30
NASDAQ: 𝑛2 = 25 , 𝑋̄2 = 2.53 , 𝑆2 = 1.16
Assuming both populations are approximately normal with equal variances, is
there a difference in mean
yield ( = 0.05)?
Solution:
(𝜎1 & 𝜎2 𝑢𝑛𝑘𝑛𝑜𝑤𝑛) (𝜎1 = 𝜎2 ) t
Step 1: state the hypothesis:
𝐻0 : 𝜇`1 = 𝜇2
𝐻1 : 𝜇1 ≠ 𝜇2
Test is two-tailed test (key word is difference between 2 samples)
Step 2- Select the level of significance and critical value.
α = 0.05 as stated in the problem
±𝑡(𝛼 ,𝑛 ±𝑡 0.05 ±𝑡(0.025 ,44)=±2.0154
2 1 +𝑛2 −2)= ( ,21+25−2)=
2

Step 3: Select the test statistic.

1
 Use Z-distribution since the assumptions are met

(𝑛1 − 1)𝑆12 + (𝑛2 − 1)𝑆22 (21 − 1) × 1.32 + (25 − 1) × 1.162

𝑆𝑝2 = =
(𝑛1 − 1) + (𝑛2 − 1) (21 − 1) + (25 − 1)
33.8 + 32.2944 66.0944
= = = 1.5021
44 44

3.27 − 2.53 0.74

𝑡𝑠𝑡𝑎𝑡 = = = 2.040
0.3627
√1.5021( 1 + 1 )
21 25

Step 4: Formulate the decision rule. (Critical value)

Reject 𝐻0 if 𝑡𝑐 >2.0154 Or 𝑡𝑐 < −2.0154
Step 5: Make a decision and interpret the result.

Reject H0 at a = 0.05
There is evidence of a difference in means.
Since we rejected H0 can we be 95% confident that µNYSE > µNASDAQ?

2
95% Confidence Interval for µNYSE - µNASDAQ

1 1
(𝑋1 − 𝑋2 ) ± 𝑡𝛼/2 √𝑆𝑝2 ( + ) = 0.74 ± 2.0154 × 0.3628 = (0.009, 1.471)
𝑛1 𝑛2

Since 0 is less than the entire interval, we can be 95% confident that µNYSE >
µNASDAQ

3
Example (2)
Assume you send your salespeople to a “customer service” training
workshop. Has the training made a difference in the number of complaints
(at the 0.01 level)? You collect the following data:

Number of Number of
Salesperson Complaints Complaints
Before After
C.B. 6 4
T.F. 20 6
M.H. 3 2
R.K. 0 0
M.O. 4 0

Solution:
Step 1: state the hypothesis:
H0: μD = 0
H1: μD  0

4
 Step2: Select the level of significance and critical value.
t0.005 = ± 4.604 d.f. = n - 1 = 4
Step 3: Find the appropriate test statistic.

(D − D ) (D − D )
Number of Number of 2
Salesperso Complaints Complaints D
n i i
Before After (X2-X1)
C.B. 6 4 -2 -2-(-4.2)= 2.2 4.84
T.F. 20 6 -14 -14-(-4.2)=-9.8 96.04
M.H. 3 2 -1 -1-(-4.2)= 3.2 10.24
R.K. 0 0 0 0-(-4.2)=4.2 17.64
M.O. 4 0 -4 4-(-4.2)=0.2 0.04
Total -21 128.8

∑ 𝑫𝒊 −𝟐𝟏
̄ =
𝑫 = = −𝟒. 𝟐
𝒏 𝟓

̅ )2
∑(𝐷𝑖 − D 128.8
SD = √ =√ = 5.6745
n−1 4

̄
𝑫 −𝟒. 𝟐 −𝟒. 𝟐
𝒕𝒄 = = = = −𝟏. 𝟔𝟔
𝑺𝑫 𝟓. 𝟔𝟕𝟒𝟓⁄ 𝟐. 𝟓𝟑𝟕𝟕
⁄ 𝟐. 𝟐𝟑𝟔𝟏
√𝒏

5
Step 4: State the decision rule
Reject H 0 if
t c  4.604
or
t c  −4.604

Step 5: Decision Reject H0

Do not reject H0 (tstat is not in the rejection region)
There is insufficient of a change in the number of complaints.
Since this interval contains 0 you are 99% confident that μD = 0
Do not reject H 0

-The Paired Difference Confidence Interval μD is:

𝑆𝐷
𝜇̂ 𝐷 = 𝐷 ± 𝑡𝛼/2
√𝑛
5.6745
= −4.2 ± 4.604
√5
= −4.2 ± 11.6836
−15.87 < 𝜇̂ 𝐷 < 7.48

6
Example (3)
Is there a significant difference between the proportion of men and the proportion
of women who will vote Yes on Proposition A?
In a random sample, 36 of 72 men and 35 of 50 women indicated they would
vote Yes
Test at the .05 level of significance
Solution:
Step 1: State the null and alternate hypotheses.
H0: π1 – π2 = 0 (the two proportions are equal)
H1: π1 – π2 ≠ 0 (there is a significant difference between proportions)
Step 2: State the level of significance and critical value.
The .05 significance level is stated in the problem.
±𝑍𝛼 = ±𝑍0.05 = ±𝑍0.025
2 2

±𝑍0.025 = ±1.96

7
Step 3: Find the appropriate test statistic.
The sample proportions are:

Men: p1 = 36/72 = 0.50

Women: p2 = 35/50 = 0.70
The pooled estimate for the overall proportion is:
𝑋1 + 𝑋2 36 + 35 71
𝑝= = = = .582
𝑛1 + 𝑛2 72 + 50 122

(𝑝1 − 𝑝2 ) − (𝜋1 − 𝜋2 )
𝑧STAT =
1 1
√𝑝(1 − 𝑝) ( + )
𝑛1 𝑛2
(.50 − .70) − (0)
= = −2.20
1
√.582(1 − .582) ( + ) 1
72 50
Step 4: State the decision rule

Zc  Z Z c  −Z 
Reject H0 if 2 Or 2

Z c  1.96 Or Z c  −1.96

8
Step 5:Decision Reject H0
There is evidence of a significant difference in the proportion of men and women
who will vote yes.
The confidence interval for
π1 – π2 is:

𝑝1 (1 − 𝑝1 ) 𝑝2 (1 − 𝑝2 )
(𝑝1 − 𝑝2 ) ± 𝑍𝛼/2 √ +
𝑛1 𝑛2

The 95% confidence interval for π1 – π2 is:

0.50(0.50) 0.70(0.30)
(0.50 − 0.70) ± 1.96 √ +
72 50
= (-0.37, -0.03)
Since this interval does not contain 0 can be 95% confident the two proportions are
different.

9
Example (4)
You are a financial analyst for a brokerage firm. Is there a difference in dividend
yield between stocks listed on the NYSE & NASDAQ? You collect the following
data:
NYSE: 𝑛1 = 21 , 𝑆1 = 1.30
NASDAQ: 𝑛2 = 25 , 𝑆2 = 1.16
Is there a difference in the variances between the NYSE & NASDAQ at the
 = 0.05 level?
Step 1: state the hypothesis:
H0: σ21 = σ22 (there is no difference between variances)
H1: σ21 ≠ σ22 (there is a difference between variances)

Step2: Select the level of significance and critical value.

Find the F critical value for  = 0.05:
Numerator d.f. = n1 – 1 = 21 –1 =20
Denominator d.f. = n2 – 1 = 25 –1 = 24

Fα/2 = F.025, 20, 24 = 2.33

10
Step 3: Find the appropriate test statistic.
The test statistic is:
𝑆12 1.302
𝐹𝑆𝑇𝐴𝑇 = 2= = 1.256
𝑆2 1.162

Step 4: State the decision rule

Reject H0 if FSTAT > Fα/2 =2.33

FSTAT = 1.256 is not in the rejection region, so we do not reject H0

Step 5: Decision Reject H0
There is not sufficient evidence of a difference in variances at  = .05
Do not reject H0, there is insufficient evidence that the population variances are
different at  = .05
√ H0: σ21 = σ22 (there is no difference between variances)
× H1: σ21 ≠ σ22 (there is a difference between variances)

11
12
Example (5)page 372 & 373
Waiting time is a critical issue at fast-food chains, which not only want to
minimize the mean service time but also want to minimize the variation in the
service time from customer to customer .One fast-food chain carried out a study to
measure the variability in the waiting time (defined as the time in minutes from
when an order was completed to when it was delivered to the customer ) at lunch
and breakfast at one of the chain’s stores. The results were as follows:
𝐿𝑢𝑛𝑐ℎ: 𝑛1 = 25 , 𝑆12 = 4.4
Breakfast:𝑛2 = 21 , 𝑆22 =1.9
At the 0.05 level of significance, is there evidence that there is more variability in
the service time at lunch than at breakfast? Assume that the population service
times are normally distributed
Solution
1)
𝐻0 : 𝜎12 ≤ 𝜎22
𝐻1 : 𝜎12 > 𝜎22

2)
𝐹𝛼,𝑛1−1,𝑛2−1 = 𝐹0.05,25−1,21−1 = 𝐹0.05,24,20 = 2.08
3)
𝑆12 4.4
𝐹𝑠𝑡𝑎𝑡 = 2 = = 2.3158
𝑆2 1.9
4)
Reject 𝐻0 if 𝐹𝑠𝑡𝑎𝑡 > 2.08

13
5) because 𝐹𝑠𝑡𝑎𝑡 = 2.3158 > 2.08,you reject 𝐻0 .using a 0.05 level of
significance, you conclude that there is evidence that there is more variability in
the service time at lunch than at breakfast.
Reject the null hypothesis, there was a significant difference between two
variances (σ12 ≠ σ22 ). The test statistic will be use is Separate variance t-test
× 𝐻0 : 𝜎12 ≤ 𝜎22
√ 𝐻1 : 𝜎12 > 𝜎22

14
Example (6)
An experiment has a Sigle factor with four groups and nine values in each group.
If SSA=752, SST=1250
Answer the following questions:
1) How many degrees of freedom are there in determining
the among-group variation?
2) How many degrees of freedom are there in determining
the within-group variation?
3) How many degrees of freedom are there in determining
the total variation?
4) What is SSW?
5) What is MSA?
6) What is MSW?
7) What is the value of 𝐹𝑠𝑡𝑎𝑡 ?
Solution:
1) How many degrees of freedom are there in determining
The among-group variation?
c-1=4-1=3
2) How many degrees of freedom are there in determining
The within-group variation?
n-c=9-4=5
3) How many degrees of freedom are there in determining
The total variation?
n-1=9-1=8
4)What is SSW?
SST-SSA=1250-752=498
5)What is MSA?

15
 752
𝑀𝑆𝐴 = = 250.67
3
6)What is MSW?
498
𝑀𝑆𝑊 = = 99.6
5

7)What is the value of 𝐹𝑠𝑡𝑎𝑡 ?

𝑀𝑆𝐴 250.67
𝐹𝑠𝑡𝑎𝑡 = = = 2.52
𝑀𝑆𝑊 99.6

16
 Example(7) (Slide 65-68)
You want to see if three different golf clubs yield different distances. You
randomly select five measurements from trials on an automated driving machine
for each club. At the 0.05 significance level, is there a difference in mean distance?
Club 1 Club 2 Club 3
254 234 200
263 218 222
241 235 197
237 227 206
251 216 204
Total 1246 1130 1029
Mean 249.2 226 205.8
𝑋̿ = 227

C=3 n=15
SSA = 4716.4 , SSW = 1119.6
Solution:

Source of variation Degrees of Sum of Mean Squares F- ratio

(S.V) freedom Squares (S.S) (MS)
Among groups c-1=3-1=2 SSA=4716.4 MSA =SSA/c-1 FSTAT = MSA /
4716.4 MSW
2 2358.2
= 2358.2 =
93.3
= 25.275
Within groups n-c=15- SSW=1119.6 MSW = SSW/n-c
3=12 1119.6
= 93.3
12
Total n-15-1=14 SST=5836

Step (1) : State the null and alternate hypotheses :

17
H0 : µ1 = µ2 = µ3

H1 : Not all 𝜇𝑗 are equal(Not all the means are equal.).

Step (2): Select the level of significance (α =0.05)

Step (3): The test statistic :

𝑀𝑆𝐴 𝑆𝑆𝐴⁄𝑐 − 1 4716.4⁄3 − 1
𝐹𝑆𝑇𝐴𝑇 = = = = 25.275
𝑀𝑆𝑊 𝑆𝑆𝑊 ⁄𝑛 − 𝑐 1119.6⁄15 − 3
Step (4): The critical value:
The degrees of freedom for the numerator (c-1) = 3-1 =2
The degrees of freedom for the denominator (n-c) = 15-3 =12
F(0.05 , 2 ,12 ) = 3.89
Step (5) : Formulate the decision Rule and make a decision
FSTAT (25.275) > F(0.05 ,2,12) (3.89)

Reject Ho at α =0.05

18