NAME: ANNALYN M.

AKMAD Program: MAEd – EM

EXERCISE No. 4

1. The directors of a small college find it necessary to increase the size of classes. A special
film, utilizing the most advanced propaganda techniques presents the advantages of larger
size of classes. It is anticipated that more favorable attitudes (i.e. higher scores) will result
from exposure to the film. Use 1% level of significance to test the hypothesis.

Before 25 23 30 7 3 22 12 30 5 14
After 28 19 34 10 6 26 13 47 16 9

Solution:

Step 1. H0: µ1 = µ2, That the mean average of favorable attitudes (higher score) before and after watching the film is the same or do not differ

significantly.

Ha: µ1 > µ2, That the mean average of favorable attitude (higher score) before exposure to the film is higher than after.

Step 2. Test- Statistic: Use t-test for dependent samples

Step 3. Level of Significance: Use α= 0.05 level of significance

Step 4. Decision Criterion: Reject H0 if tc ≥ t α (n-1) df = t0.05 (10-1) = 1.833

Table 1.

Individual Before After Di Di

2

1 25 28 -3 9
2 23 19 4 16
3 30 34 -4 16
4 7 10 -3 9
5 3 6 -3 9
6 22 26 -4 16
7 12 13 -1 1
8 30 47 -17 289
9 5 16 -11 121
10 14 9 5 25
Total 171 208 -37 511

Note: Solution/Computation is on the next page.

Step 6. Decision: Since tc = -1.8148 < t0.05 (10-1) = 1.833, we do not reject the H0

Step 7. Conclusion: Based on the result, it can be concluded that the mean average of
favorable attitudes (higher score) before and after watching the film is the same or do not
differ significantly at 5% level.
2. Two samples of 8 high school seniors each has been matched on IQ before beginning an
experiment in learning words, after which they tested for the number of words learned. Group
A studied in pairs, one student reading the words to other; the students in Group B studied
alone. The following table shows the results:

NUMBER OF WORDS LEARNED

GROUP A GROUP B
20 25
13 15
15 20
10 15
18 16
10 11
20 15
12 20

Is there a significant difference at 5% level in the number of the words learned between
Group A and Group B?

Solution:

Step 1. H0: µ1 = µ2, that there is no significant difference in the number of words learned between the two groups (studied in pairs and studied

alone).

Ha: µ1 ≠ µ2, that there is a significant difference in the number of words learned between the two groups (studied in pairs and studied

alone).

Step 2. Test- Statistic: Use t-test for dependent samples

Step 3. Level of Significance: Use α= 0.05 level of significance

Step 4. Decision Criterion: Reject H0 if tc ≤ t α (n-1) df = t0.05 (8-1) = 1.895

Table 2.

GROUP A GROUP B Di Di
2

20 25 -5 25
13 15 -2 4
15 20 -5 25
10 15 -5 25
18 16 2 4
10 11 -1 1
20 15 5 25
12 20 -8 64
SUM 118 137 -19 173
MEAN 14.75 17.125

Note: Solution/Computation is on the next page.

Step 6. Decision: Since tc = -1.5717 < t0.05 (10-1) = 1.895, we do not reject the H0

Step 7. Conclusion: Based on the result, it can be concluded that there is no significant
difference in the number of words learned between the two groups (studied in pairs and
studied alone).
3. A course is designed to increase readers’ speed and comprehension. To evaluate
the effectiveness of this course, a test is given both before and after course, and
sample results follow. At the 0.05 significance level, test the claim that the scores are
higher after the course.

Before 110 90 100 168 200 98 112 123 110 103

After 120 115 150 175 180 125 130 127 112 118

Solution:

Step 1. H0: µ1 = µ2, that the course has no effect on the reader’s speed and comprehension before and after the course or they do not differ

significantly.

Ha: µ1 > µ2, that the reader’s speed and comprehension after the course is greater than or increases than before.

Step 2. Test- Statistic: Use t-test for dependent samples

Step 3. Level of Significance: Use α= 0.05 level of significance

Step 4. Decision Criterion: Reject H0 if tc ≥ t α (n-1) df = t0.05 (10-1) = 1.833

Table 3.

Reader Before After Di 2

Di
1 110 120 -10 100
2 90 115 -25 625
3 100 150 -50 2500
4 168 175 -7 49
5 200 180 20 400
6 98 125 -27 729
7 112 130 -18 324
8 123 127 -4 16
9 110 112 -2 4
10 103 118 -15 225
SUM 1214 1352 -138 4972
MEAN 121.4 135.2 -

Note: Solution/Computation is on the next page.

Step 6. Decision: Since tc = -2.3637 < t0.05 (10-1) = 1.833, we do not reject the H0

Step 7. Conclusion: Based on the result, it can be concluded that the course has no effect
on the reader’s speed and comprehension before and after the course or they do not differ
significantly.
4. A pill designed to lower systolic blood pressure is administered to 10 randomly
selected volunteers. The results are as follows:

Volunteer 1 2 3 4 5 6 7 8 9 10
Before 120 120 160 98 115 110 180 190 138 128
Pill
After Pill 90 115 120 105 90 90 180 100 100 110

At 0.05 level of significance, test the claim that systolic blood pressure is not affected
by the pill. That is, test the claim that the before and after values are equal.

Solution:

Step 1. H0: µ1 = µ2, that the pill has no effect on systolic blood pressure, and the mean blood pressure before and after taking the pill is the

same.

Ha: µ1 ≠ µ2, that the pill does have an effect on systolic blood pressure, meaning the before and after values are not equal.

Step 2. Test- Statistic: Use t-test for dependent samples

Step 3. Level of Significance: Use α= 0.05 level of significance

Step 4. Decision Criterion: Reject H0 if tc ≥ t α (n-1) df = t0.05 (10-1) = 1.833

Table 4.

Volunteer Before Pill After Pill Di Di

2

1 120 90 30 900
2 120 115 5 25
3 160 120 40 1600
4 98 105 -7 49
5 115 90 25 625
6 110 90 20 400
7 180 180 0 0
8 190 100 90 8100
9 138 100 38 1444
10 128 110 18 324
SUM 1359 1100
MEAN 135.9 110

Note: Solution/Computation is on the next page.

Step 6. Decision: Since tc = 2.9887 > t0.05 (10-1) = 1.833, reject the H0

Step 7. Conclusion: Based on the result, it can be concluded that the pill does have an
effect on systolic blood pressure, meaning the before and after values are not equal.
5. Trace metals in drinking water affect the flavor and an unusually high concentration
can pose a health hazard. Ten pairs of data were taken measuring zinc concentration
in bottom water and surface water. Does the data suggest that the true average
concentration in the bottom water exceeds that of surface water?

PLACE OF ZINC LOCATION

CONCENTRATION 1 2 3 4 5 6 7 8 9 10
Bottom Water .430 .266 .567 .531 .707 .716 .651 .589 .469 .723
Surface Water .415 .238 .390 .410 .605 .609 .632 .523 .411 .612

Solution:

Step 1. H0: µ1 = µ2, that the average concentration of zinc in bottom water is equal in surface water.

Ha: µ1 ≥ µ2, that the average concentration of zinc in bottom water greater than in surface water.

Step 2. Test- Statistic: Use t-test for dependent samples

Step 3. Level of Significance: Use α= 0.05 level of significance

Step 4. Decision Criterion: Reject H0 if tc ≥ t α (n-1) df = t0.05 (10-1) = 1.833

Table 5.

Location Bottom Water Surface Water Di Di

2

1 0.430 0.415 0.015 0.000225

2 0.266 0.238 0.028 0.000784
3 0.567 0.39 0.177 0.031329
4 0.531 0.41 0.121 0.014641
5 0.707 0.605 0.102 0.010404
6 0.716 0.609 0.107 0.011449
7 0.651 0.632 0.019 0.000361
8 0.589 0.523 0.066 0.004356
9 0.469 0.411 0.058 0.003364
10 0.723 0.612 0.111 0.012321
SUM 5.649 4.845 0.804 0.089234
MEAN 0.5649 0.4845

t-Test: Paired Two Sample for Means

Bottom Water Surface Water

Mean 0.5649 0.4845
Variance 0.021544767 0.017221167
Observations 10 10
Pearson Correlation 0.935348815
Hypothesized Mean Difference 0
df 9
t Stat 4.863812745
P(T<=t) one-tail 0.000445558
t Critical one-tail 1.833112933
P(T<=t) two-tail 0.000891115
t Critical two-tail 2.262157163

Note: Solution/Computation is on the next page.

Step 6. Decision: Since tc = 4.8638 ¿ t0.05 (10-1) = 1.833, we reject the H0

Step 7. Conclusion: Based on the result, it can be concluded that the that the average
concentration of zinc in bottom water greater than in surface water.
NAME: ANNALYN M. AKMAD Program: MAEd – EM

EXERCISE 5
T-TEST FOR INDEPENDENT SAMPLES
1. Do left-handed persons type slower than right- handed persons? The
mean time to type an article for a random sample of 8 left- handed
persons is 133.8 min with standard deviation of 14.7 min. While for a
random sample of 11 right- handed persons, the mean time is 136.2
min with standard deviation equal to 15.0 min. Test the hypothesis
at 5% level of significance.
Left-Handed Persons Right-Handed
Persons
SAMPLE SIZE 8 11
MEAN 133.8 136.2
STANDARD 14.7 15.0
DEVIATION
VARIANCE
 2. To find out whether a new serum will arrest leukemia, 9 mice which
have all reached an advanced stage of the disease, are selected.
Four mice received the treatment and five do not. The survival times
in months, from the time the experiment commenced are as follows:
TREATED NOT TREATED
5.9 3.1
4.5 4.8
5.8 1.4
4.8 0.5
Test the hypothesis at 1% level of significance.

Solution:

a. Test the quality of variances.

2 2
H0 : σ 1=σ 2

2 2
Ha : σ 1 ≠ σ 2

b. Test- Statistic: Use F-test at α = 0.01

c. Decision Criterion: Reject H0 if Fc ≥ F 0.01 (3,4) = 16.69

d. Computation of the Test-Statistic:

larger variance
Fc =
smaller variance

TREATED NOT TREATED

5.9 3.1
4.5 4.8
5.8 1.4
4.8 0.5
0.9
n 4 5
Total 21 10.7
Mean 5.25 2.14
Variance 0.496667 3.193

3.193
Fc = = 6. 4289
0.496667

e. Decision: Since Fc = 6.4289 ¿ F 0.01 (3,4) = 16.69, we failed to reject the H0

f. Conclusion: H0: σ 21=σ 22

From the result of the comparison of the variances of the new serum treatment for the four
mice (with treatment) and five (without treatment), the following is undertaken to the solve the
main problem:

Step 1.

H0: µ1=µ2 That the new serum does not significantly arrest leukemia.
 Ha: µ1 ≠ µ2 That the new serum does significantly arrest leukemia.

Step 2. Test-Statistics: Use t-test for independent samples

Step 3. Level of Significance: Use α = 0.01 level of significance

Step 4. Decision Criterion: Reject H0 if |t C|≥t 0.01 (4+5-2) = 2.998

Step 5. Computation:

T-Test: Two-Sample Assuming Unequal Variances

Not
Treated Treated
Mean 5.25 2.14
Variance 0.496667 3.193
Observations 4 5
Hypothesized Mean Difference 0
df 5
t Stat 3.560939
P(T<=t) one-tail 0.008099
t Critical one-tail 3.36493
P(T<=t) two-tail 0.016198
t Critical two-tail 4.032143
Note: Solution/Computation on the next page.

Step 6. Since |t C|=3.5609 ≥ t 0.01 (4+5-2) = 2.998, reject H0

Step 7. Conclusion: The data indicate that the new serum does significantly arrest
leukemia.
 3. In a study designed to monitor the movement of ammonia ions in the
soil, radioactive nitrogen ¿ ¿) was introduced into soil cores. Uptake of
¿ ¿) into microbial biomass in the soil was recorded at the end of 7
days. The soil examined were either bare or planted to onions. The
results of the uptake experiment are given below:

SOIL ¿ ¿) (picograms)
With Plant 18 15 12 8 15
Cover
Without 22 24 20 28 28 25
Plant Cover
Determine if plant cover significantly reduced uptake of labelled
nitrogen by microorganisms in the soil.

Solution:

a. Test the quality of variances.

2 2
H0 : σ 1=σ 2

2 2
Ha : σ 1 ≠ σ 2

b. Test- Statistic: Use F-test at α = 0.05

c. Decision Criterion: Reject H0 if Fc ≤ F 0.05 (4,5) = 5.19

d. Computation of the Test-Statistic:

larger variance
Fc =
smaller variance

SOIL

With Plant Cover Without Plant Cover

18 22
15 24
12 20
8 28
15 28
25
Mean 13.6 24.5
Variance 14.3 10.3

14.3
Fc = = 1.3883
10.3

e. Decision: Since Fc ¿ 1.3882<¿ F 0.05 (4,5) = 5.19, reject the H0

f. Conclusion: H0: σ 21 ≠ σ 22

From the result of the comparison of the variances of the plant with cover and without cover,
the following is undertaken to the solve the main problem:
 Step 1.

H0: µ1=µ2 That the movement of ammonia ions in the soil with plant
cover is equal to the ammonia ions in the soil of without plant cover.

Ha: µ1 ≠ µ2 That the movement of ammonia ions in the soil with plant
cover is lower to the ammonia ions in the soil of without plant cover.

Step 2. Test-Statistics: Use t-test for independent samples

Step 3. Level of Significance: Use α = 0.05 level of significance

Step 4. Decision Criterion: Reject H0 if t C ≤ t 0.05 (df)

t-Test: Two-Sample Assuming Unequal Variances

With Plant Cover Without Plant Cover

Mean 13.6 24.5
Variance 14.3 10.3
Observations 5 6
Hypothesized Mean Difference 0
df 8
t Stat -5.095089963
P(T<=t) one-tail 0.000467754
t Critical one-tail 1.859548038
P(T<=t) two-tail 0.000935507
t Critical two-tail 2.306004135
Note: Solution/Computation on the next page.

Step 6. Decision: Since t C =−5.0951 ≤t 0.05(8) = 1.860, we reject H0

Step 7. Conclusion: That the movement of ammonia ions in the soil with plant
cover is lower to the ammonia ions in the soil of without plant cover.

GROUP YEAR

1 2 3 4 5 6 7 8
Active 80 85 85 88 84 85 83 83
Not Active 90 90 92 91 88 80 79 80
 4. To determine whether active participation in extra- curricular
activities is detrimental to one’s grades, the following grade-point
averages were collected over a period of 8 years.
Assuming the population to be normally distributed, test at 5% level of
significance whether to participate actively in school extra- curricular
activities is detrimental to one’s grades.

Solution:

a. Test the quality of variances.

2 2
H0 : σ 1=σ 2

2 2
Ha : σ 1 ≠ σ 2

b. Test- Statistic: Use F-test at α = 0.05

c. Decision Criterion: Reject H0 if Fc ≥ F 0.05 (8,8) = 3.44

d. Computation of the Test-Statistic:

larger variance
Fc =
smaller variance

YEAR
ACTIVE NOT ACTIVE
80 90
85 90
85 92
88 91
84 88
85 80
83 79
83 80
Mean 84.125 86.25
Variance 5.267857 31.07143

31.07143
Fc = = 5.8983
5.267857

e. Decision: Since Fc ¿ 5.8983>¿ F 0.05 (8,8) = 3.44, reject the H0

f. Conclusion: H0: σ 21 ≠ σ 22

From the result of the comparison of the variances of the

Step 1.

H0: µ1=µ2 That active participation in extra-curricular activities does

significantly detrimental to one’s grade.

Ha: µ1 ≠ µ2 That active participation in extra-curricular activities does not

significantly detrimental to one’s grade.

Step 2. Test-Statistics: Use t-test for independent samples

Step 3. Level of Significance: Use α = 0.05 level of significance

 Step 4. Decision Criterion: Reject H0 if t C ≥ t 0.05 (df)

ACTIVE NOT ACTIVE

Mean 84.125 86.25
Variance 5.267857143 31.07142857
Observations 8 8
Pooled Variance 18.16964286
Hypothesized Mean Difference 0
df 14
t Stat -0.997047238
P(T<=t) one-tail 0.167831699
t Critical one-tail 1.761310136
P(T<=t) two-tail 0.335663398
t Critical two-tail 2.144786688
Note: Solution/Computation on the next page.

Step 6. Decision: Since t C =−0.9970 ≤ t 0.05 (8) = 1.860, we failed to reject H0

Step 7. Conclusion: That active participation in extra-curricular activities does

not significantly detrimental to one’s grade.

NEW MACHINE OLD MACHINE

42.1 41.3 42.4 43.2 41.8 42.7 43.8 42.5 43.1 44.0
41.0 41.8 42.8 42.3 42.7 43.6 43.3 43.5 41.7 44.1
5. In a packing plant, a machine packs cartons with jars. It is supposed
that a new machine will pack faster on the average than the machine
currently used. To test that hypothesis, the times it takes each
machine to pack ten cartons are recorded. The results, in seconds,
are shown in the following table.
Do the data provide sufficient evidence to conclude that, on the average,
the new machine packs faster? Perform the required hypothesis testing at
the 5% level of significance.

Solution:

a. Test the quality of variances.

2 2
H0 : σ 1=σ 2
 2 2
Ha : σ 1 ≠ σ 2

b. Test- Statistic: Use F-test at α = 0.05

c. Decision Criterion: Reject H0 if Fc ≥ F 0.05 (9,9) = 3.18

d. Computation of the Test-Statistic:

larger variance
Fc =
smaller variance

NEW MACHINE OLD MACHINE

1 42.1 42.7
2 41.3 43.8
3 42.4 42.5
4 43.2 43.1
5 41.8 44.0
6 41.0 43.3
7 41.8 43.6
8 42.8 43.5
9 42.3 41.7
10 42.7 44.1
Mean 42.14 43.23
Variance 0.467111 0.5061

0.5061
Fc = = 1.0835
0.4671

e. Decision: Since Fc ¿ 1.0835<¿ F 0.05 (9,9) = 3.18, we do not reject the H0

f. Conclusion: H0: σ 21=σ 22

From the result of the comparison of the variances of the

Step 1.

H0: µ1=µ2 that the mean average that the new machine packs is equal
to the mean average of the machine currently used.

Ha: µ1 ≠ µ2 that the mean average that the new machine packs is greater
to the mean average of the machine currently used.

Step 2. Test-Statistics: Use t-test for independent samples

Step 3. Level of Significance: Use α = 0.05 level of significance

Step 4. Decision Criterion: Reject H0 if t C ≥ t 0.05 (df)

t-Test: Two-Sample Assuming Equal Variances

NEW MACHINE OLD MACHINE

Mean 42.14 43.23
Variance 0.467111111 0.562333333
Observations 10 10
Pooled Variance 0.514722222
Hypothesized Mean Difference 0
df 18
 t Stat -3.397230706
P(T<=t) one-tail 0.001605571
t Critical one-tail 1.734063607
P(T<=t) two-tail 0.003211143
t Critical two-tail 2.10092204
Note: Solution/Computation on the next page.

Step 6. Decision: Since t C =−3.3972 ≤t 0.05(18) = 1.734, we failed to reject H0

Step 7. Conclusion: The mean average that the new machine packs is equal to
the mean average of the machine currently used.

NAME: ANNALYN M. AKMAD Program: MAEd – EM

EXERCISE
ONE WAY AND TWO-WAY CLASSIFICATION ANOVA

1. A pilot does extensive bad weather flying and decides to buy a

battery-powered radio as an independent back- up for her regular
radios, which depend on the airplane’s electrical system. She has a
choice of three brands of rechargeable batteries that vary in cost.
She obtains the sample data in the following table. She randomly
selects four batteries for each brand, and test them for operating
time (in hours) before recharging is necessary. Do the three brands
have the same mean usable time before recharging is required?
BRAND
A B C
20.7 21.0 26.5
21.9 25.6 26.7 TOTAL
20.9 24.7 25.0
22.2 24.5 24.6
n
∑y
∑y
2

y
 1. To study the effectiveness of three kinds of packaging, a processor of
a breakfast food puts each kind into 5 different supermarkets. Use
the following data representing the number of sales of the breakfast
food between 9:00 AM and noon on a given day, to test the null
hypothesis that the packaging has no effect on sales at 5% level of
significance.
PACKAGING SUPERMARKET TOTAL MEAN
1 2 3 4 5
A 45 32 36 32 40
B 37 34 46 44 34
C 35 37 48 46 35

SOLUTION:

Step 1: Calculate the Mean for Each Packaging Type

We calculate the mean sales for each type of packaging (A, B, and C).
45+32+36+32+ 40
Mean for A=
5
37+34+ 46+ 44+ 34
Mean for B=
5
35 +37+ 48+46+ 35
Mean for C=
5

Step 2: Calculate the Grand Mean

The grand mean is the average of all 15 observations across the three packaging
types.

Grand Mean=
∑ AllObservations
15

Step 3: Calculate the Sum of Squares Between Groups (SSB)

The SSB represents the variability due to difference between the packaging types.
For each type packaging, we calculate:
 k
SSB=∑ ni ¿
i=1

where:
 k is the number of groups (packaging types)
 ni is the number of observation in each group (5 in this case)
 Mean i is the mean of each packaging type
 Grand Mean is the overall mean

Step 4: Calculate the Sum of Squares Within Groups (SSW)

The SSW represents the variability within each packaging type. For each observation,
calculate the squared deviation from its group mean and sum these values.
k ni
SSW =∑ ∑ ¿ ¿ ¿
i =1 j=1

where:
 k is the number of groups (3)
 N is the total number of observations (15)

Step 6: Calculate the F-statistic

The F-statistic is given by:
MSB
F=
MSW

Step 7: Compare the F-statistic with the Critical Value

Finally, compare the calculated F-statistic with the critical value from the F-distribution
table at a 5% significance level with degrees of freedom ( k −1 , N −k ). Alternatively,
compute the p-value and compare it to α =0.05 .

If F is greater than the critical value, or if the p-value is less than α , reject the null
hypothesis, indicating that there is a significant effect of packaging on sales.

Here are the step-by-step results:

1. Mean for each packaging type:
 Mean for A: 37.0
 Mean for B: 39.0
 Mean for C: 40.2

2. Grand Mean: 38.73

 3. Sum of Squares Between Groups (SSB): 26.13
4. Sum of Squares Within Groups (SSW):410.80
5. Mean Square Between (MSB): 13.07
6. Mean Square Within (MSW): 34.23
7. F-statistic: 0.382
8. p-value: 0.691
Anova: Two-Factor Without Replication

SUMMARY Count Sum Average Variance

45 2 72 36 2
32 2 71 35.5 4.5
36 2 89 44.5 4.5
32 2 90 45 2
40 2 69 34.5 0.5

B 5 195 39 32
C 5 196 39.2 25.2

ANOVA
Source of Variation SS df MS F P-value F crit
Rows 215.4 4 53.85 16.07463 0.009888 6.388233
Columns 0.1 1 0.1 0.029851 0.871219 7.708647
Error 13.4 4 3.35

Total 228.9 9

Conclusion
Since the p-value (0.691) is greater than the significance level α =0.05 , we fail to
reject the null hypothesis. This indicates that there is no statistically significant effect
of packaging type on sales at the 5% level of significance.
3. Suppose the National Transportation Safety Board (NTSB) wants to examine the
safety of compact cars, midsize cars, and full- size cars. It collects a sample of three
for each of the treatments (cars types). Using the data provided below, test whether
the mean pressure applied to the driver’s head during a crash test is equal for each
type of cars. Use 5% level of significance for testing the hypothesis.

CARS
COMPACT MIDSIZE FULL SIZE
640 465 480
650 422 450 TOTAL
700 520 400

SOLUTION:

To solve this problem, we need to perform a one-way ANOVA test to check if

there is a significant difference in the mean pressure applied to the driver’s head
during a crash test for each car type.

The data provided is:

Car Type Sample 1 Sample 2 Sample 3
Compact 640 650 700
Midsize 465 422 520
Full-size 480 450 400

Steps to solve:
1. State the hypotheses:
 Null Hypotheses ( H 0): The mean pressure is the same for all car types ¿
 Alternative Hypotheses ( H 1): At least one car type has a mean pressure
different from the others.

2. Calculate the Means and Variances:

 Calculate the mean pressure for each car type and the overall mean.

3. Calculate the Sum of Squares:

 Total Sum of Squares (SST): Measures the total variation in the data.
 Between-Group Sum of Squares (SSB): Measures the variation
between the group means.
 Within-Group Sum of Squares (SSW): Measures the variation within
each group.

4. Calculate the Mean Squares:

 Mean Square Between (MSB)= SSB/(k−1), where k is the number of
groups.
 Mean Square Within (MSW)= SSW /(N −k ), where N is the total number
of observations.

5. Calculate the F-statistic:

MSB
 F=
MSW
 6. Determine the Critical Value and Conclusion:
 Use a significant level of 0.05 and compare the calculated F-statistic to
the critical value from the F-distribution table with degrees of freedom
df between=k−1 and df within=N−k
 If the calculated F is greater than the critical F, reject H 0: otherwise, fail
to reject H 0.

Step 1: Calculate the Means

 Compact Mean: (640+650 +700)/3=663.33
 Midsize Mean: (465+422+520)/3=469.00
 Full-size Mean: (480+450+ 400)/3=443.33
 Overall Mean: (640+650 +700+465+ 422+520+ 480+450+ 400)/9=516.67

Step 2: Calculate Sum of Squares

The sum of squares are as follows:
 Sum of Squares Between (SSB): 86824.22
 Sum of Squares Within (SSW): 10159.33
 Total Sum of Squares (SST): 96983.56

Step 3: Calculate the Mean Squares

1. Degrees of Freedom Between ( df between ) :k −1=3−1=2
2. Degrees of Freedom Within ( df within ) : N−k =9−3=6

SSB
 Mean Square Between (MSB):
df between
SSW
 Mean Square Within (MSW):
df within

The calculated values are:

 Mean Square Between (MSB): 43412.11
 Mean Square Within (MSW): 1693.22
Anova: Single Factor

SUMMARY
Groups Count Sum Average Variance
COMPACT 3 1990 663.3333 1033.333
MIDSIZE 3 1407 469 2413
FULL SIZE 3 1330 443.3333 1633.333

ANOVA
Source of Variation SS df MS F P-value F crit
Between Groups 86824.22 2 43412.11 25.63876 0.001149 5.143253
Within Groups 10159.33 6 1693.222

Total 96983.56 8
 F-Statistic: 25.64
Step 4: Conclusion
At a 5% significance level, we need to compare the calculated F-statistic to the critical
value for df between=2 and df within=6 . The critical F-value for α =0.05 is approximately
5.14.

Since the calculated F-statistic (25.64) is much greater than the critical value (5.14),
we reject the null hypothesis.

Therefore, There is a significant difference in the mean pressure applied to the

driver’s head during a crash test among the different types of cars (compact, midsize,
and full-size).

4. The following data represent the final grades obtained by five students in
Mathematics, English, Values Education, and Biology:

STUDENT SUBJECT
Math English Values Biology
1 80 78 85 79
2 86 90 93 91
3 75 78 83 79
4 78 80 84 76
5 83 87 85 87
Use 0.05 level of significance to test the hypotheses that
a. Students have equal ability.
b. Courses are of equal difficulty level.
To solve this problem, we need to perform a two-way ANOVA test. We will test two
hypotheses:
1. Students have equal ability (row effect).
2. Courses are of equal difficulty level (column effect).

Step-by-Step Solution
Step 1: Set up the Hypotheses
For each hypothesis:
 For students (rows):
o H 0: All students have the same average ability.
o H 1: At least one student has a different average ability.
 For courses (columns):
o H 0: All courses are of equal difficulty level.
o H 1: At least one course has a different difficulty level.

Step 2: Calculate the Mean of Each Row and Each Column

Let’s denote the subjects as follows:
 Math (Column 1)
 English (Column 2)
 Values (Column 3)
 Biology (Column 4)

The data is given as:

Student Math English Values Biology
1 80 78 85 79
2 86 90 93 91
3 75 78 83 79
4 78 80 84 76
5 83 87 85 87

Calculate the row and column means.

Step 3: Calculate the Grand Mean

The grand mean is the mean of all scores.
∑ All Scores
Grand Mean=
Total Number of Scores

Step 4: Calculate the Sum of Squares

1. Total Sum of Squares (SST):
SST =∑ ¿

2. Sum of Squares for Rows

SSR=∑ n¿
Where n is the number of columns (subjects).

3. Sum Squares for Columns (SSC):

SST =∑ m¿
Where m is the number of rows (students).

4. Error Sum of Squares (SSE):

SSE=SST −SSR−SSC

Step 5: Calculate the Mean Squares

 Mean Square for Rows (MSR):
 SSR
MSC=
df R
where df R=number of rows−1

 Mean Square for Columns (MSC):

SSC
MSC=
df C
where df C =number of columns−1

 Mean Square for Error (MSE):

SSE
MSE=
df error
where df error=(number of rows−1)( number of columns−1)

Step 6: Calculate the F-values

1. F-value for Rows (F_R):
MSR
FR=
MSE

2. F-value for Columns (F_C):

MSC
F c=
MSE

Step 7: Compare the F-Values with the Critical F-Values

Using a significance level of 0.05, find the critical F-value for the respective degrees
of freedom:
 F critical ,rows =F ( df R , df error )
 F critical ,columns =F ( df c , df error )

Compare F R and F C to their respective critical values.

 If F R > F critical , rows, reject H 0 for students (indicating different abilities).
 If F c > F critical , columns, reject H 0 for courses (indicating different difficulty levels).

Results of the two-way ANOVA calculations:

 Grand Mean: 82.85
 Total Sum of Squares (SST): 500.55
 Sum of Squares for Rows (SSR): 366.80
 Sum of Squares for Columns (SSC): 80.85
 Error Sum of Squares (SSE): 52.80

Mean Squares:
 MSR (Rows): 91.70
 MSC (Columns): 26.98
 MSE (Error): 4.40

F-Values:
 F-value for Rows (Students): 20.84
 F-value for Columns (Subjects): 6.13
Critical F-Values at α =0.05 :
 F-critical for Rows: 3.26
 F-critical for Columns: 3.49

Interpretation
1. Students’ ability (Rows):
 F row=20.84> Fcritical , row=3.26
 Conclusion: Reject H 0 for courses. This means that there is a significant
difference in difficulty levels among the courses.

2. Courses’ difficulty level (Columns):

 F column=6.13 > Fcritical , column =3.49
 Conclusion: Reject H 0 for courses. This means that there is a significant
difference in difficulty levels among the courses.

Anova: Two-Factor Without Replication

Su Varianc
SUMMARY Count m Average e
80.6666 14.3333
80 3 242 7 3
91.3333 2.33333
86 3 274 3 3
75 3 240 80 7
78 3 240 80 16
86.3333 1.33333
83 3 259 3 3

ENGLISH 5 413 82.6 30.8

VALUES 5 430 86 16
BIOLOGY 5 412 82.4 39.8

ANOVA
Source of
Variation SS df MS F P-value F crit
305.333 76.3333 14.8701 0.00089 3.83785
Rows 3 4 3 3 4 3
40.9333 20.4666 3.98701 0.06290
Columns 3 2 7 3 7 4.45897
41.0666 5.13333
Error 7 8 3

387.333
Total 3 14

Conclusion: Both hypotheses are rejected. Therefore, students do not have equal
ability.
 5. A researcher examined the effect of maintaining the water table at three
different heights on seminal root length of three cereals. Evaluate at 5% level
whether a) water table and b) type of cereal significantly affect root length.

CEREAL WATER TABLE TOTAL MEAN

LOW MEDIUM HIGH

Rice 10.3 9.6 10.8

Wheat 20.6 9.0 6.2

Oat 23.4 10.0 6.9

SOLUTION:

To evaluate whether the water table and type of cereal significantly affect root length
at the 5% significance level, we need to perform a two-way ANOVA. Here, the factors
are:

1. Water Table Level (Low, Medium, High)

2. Type of Cereal (Rice, Wheat, Oat)

The data table is as follows:

Cereal Low Medium High
Rice 10.3 9.6 10.8
Wheat 20.6 9.0 6.2
Oat 23.4 10.0 6.9

Step-by-Step Solution
Step 1: Step up the Hypotheses
For each factor:
 For water table levels:
o H 0: Water table levels has no effect on root length.
o H 1: At least one water table level has a different effect on root length.

 For cereal types:

o H 0: Cereal types have no effect on root length.
 o H 1: At least one type has a different effect on root length.

Step 2: Calculate the Mean of Each Row and Each Column

This involves calculating:
 The mean root length for each cereal type.
 The mean length for each water table level.

Step 3: Calculate the Grand Mean

The grand mean is the mean of all observations combined.
∑ All Scores
Grand Mean=
Total Number of Scores

Step 4: Calculate the Sum of Squares

1. Total Sum of Squares (SST):
SST =∑ ¿

2. Sum of Squares for Water Table Levels (SSC):

SSC=∑ n ¿
Where n is the number of cereal types

3. Sum of Squares for Cereal Types (SSR):

SSR=∑ m¿
Where m is the number of water table levels.

4. Error Sum of Squares (SSE):

SSE=SST −SSR−SSC
5. Calculate the Mean Squares
 Mean Square for Water Table Levels (MSC):
SSC
MSC=
df C
where df C =number of columns−1

 Mean Square for Cereal Types (MSR):

SSR
MSR=
df R
where df R=number of rows−1

 Mean Square for Error (MSE):

SSE
MSE=
df error
where df error=(number of rows−1)( number of columns−1)

Step 6: Calculate the F-values

1. F-value for Water Table Levels:
MSC
F C=
MSE

2. F-value for Cereal Types:

 MSR
R=
MSE

Step 7: Compare the F-values with the Critical F-values

Using a significance level of 0.05, find the critical F-values for the respective degrees
of freedom:
 F critical ,water table=F (df C , df error )
 F critical ,cereal type =F(df R , df error )

Compare F Cand F R to their respective critical values.

 If F C > F critical , water table reject H 0for water table (indicating a significant effect of
water table levels).
 If F R > F critical , cerealtype reject H0 for cereal type (indicating a significant effect of
cereal types).

Let’s proceed with these calculations.

Results and Interpretations:
 Grand Mean: 11.87
 SST (Total Sum of Squares): 286.50
 SSC (Sum of Squares for Water Table Levels): 178.53
 SSR (Sum of Squares for Cereal Types): 15.38
 SSE (Error Sum of Squares): 92.59

The mean squares and F-values are as follows:

 MSC (Mean Square for Water Table Levels): 89.26
 MSR (Mean Square for Cereal Types): 7.69
 MSE (Mean Square for Error): 23.15
 F-value for Water Table Levels: 3.86
 F-value for Cereal Types: 0.33

The critical F-value at α =0.05 for both water table levels and cereal type is
approximately 6.94.

Decision
1. For Water Table Levels: F column=3.86 < F critical=6.94 We fail to reject H 0. This
means that water table levels do not significantly affect root length at the 5%
significance level.
2. For Cereal Types: F row=0.33< F critical=6.94 We fail to reject the H 0. This means
that cereal type does not significantly affect root length at the 5% significant
level.
Anova: Two-Factor Without
Replication

Su Varianc
SUMMARY Count m Average e
10.3 2 44 22 3.92
9.6 2 19 9.5 0.5
13.
10.8 2 1 6.55 0.245
 35. 11.9333 58.2933
WHEAT 3 8 3 3
40. 13.4333 76.9033
OAT 3 3 3 3

ANOVA
Source of Variation SS df MS F P-value F crit
269.103 134.551 208.607 0.00477
Rows 3 2 7 2 1 19
5.23255 0.14942 18.5128
Columns 3.375 1 3.375 8 8 2
Error 1.29 2 0.645

273.768
Total 3 5

Conclusion
At the 5% significance level, neither the water table level nor the type of cereal
significantly affects root length.

4. The following are the data for 12 individuals’ daily sodium intake and their
systolic blood pressure readings.

PERSON SODIUM BLOOD X

2
Y
2
XY
INTAKE PRESSURE
(X) (Y)
1 5.8 150
2 7.0 160
 3 6.9 162
4 7.2 175
5 7.3 190
6 7.0 158
7 7.0 166
8 7.5 195
9 7.3 189
10 7.1 186
11 6.5 148
12 6.4 140
SUM
MEAN
A research investigator is interested in learning how strong the
association in between these variables and how well we can predict blood
pressure from sodium intake.
a. Compute a Pearson r and interpret the result.
b. Test H 0 : ρ=0at 5% level of significance.
c. Compute r 2 and explain what it means.
d. Calculate the regression equation of the data.
e. Test H 0 : β=0 at the 1% level of significance.
f. What would be a likely blood pressure for a person with a sodium intake of
6.3?

SOLUTION:

1. Compute the Pearson correlation coefficient ( r ): The Pearson correlation

coefficient, r , measures the strength and direction of the linear relationship
between sodium intake and BP.
We can calculate it using the formula:

r=
∑ (X −X )(Y −Y )
√∑ ¿¿¿¿
where X represents sodium intake, and Y represents BP.

2. Hypothesis test for H 0 : ρ=0 (at the 5% significance level): After calculating r ,
we can test if there is a significant linear relationship between sodium intake
and BP. The null hypothesis H 0 states that there is no linear relationship ( ρ=0
). If the p-value is less than 0.05, we reject H 0.

3. Compute r 2 and explain: r 2 is the coefficient of determination, which tells us the

proportion of the variance in BP that can be explained by sodium intake.

4. Calculate the regression equation: We need to find the regression line in the
form:
Y^ =a+bX
where a is the intercept and b is the slope. The slope b can be
calculated by:
 b=
∑ (X −X )(Y −Y )
∑ ¿¿¿
and the intercept a is:
a=Y −b X

5. Test H 0 : β=0 (at the 1% level of significance): This tests whether the slope b
is significantly different from 0, indicating that sodium intake significantly
predicts BP. If the p-value is less than 0.01, we reject H 0.

6. Predict BP for a sodium intake of 6.3: Using the regression equation, substitute
X =6.3 to estimate the likely BP.

Here are the results for each part:

1. Pearson correlation coefficient (r ):
r =0.823, which indicates a strong positive correlation between sodium intake
and blood pressure.

2. Hypothesis test for H 0 : ρ=0 at the 5% significance level:

The p-value for r is 0.001, which is less than 0.05. Therefore, we reject the null
hypothesis H 0, indicating a significant linear relationship between sodium
intake and blood pressure.

3. Coefficient of determination (r 2):

2
r =0.677 This means that approximately 67.7% of the variance in blood
pressure can be explained by sodium intake.

4. Regression equation:
The regression equation is:
Y^ =−53.75+32.10 · X
where Y^ is the predicted blood pressure, and X is the sodium intake.

5. Hypothesis test for H 0 : β=0 at the 1% significance level:

The p-value for the slope β is 0.001, which is less than 0.01. Thus, we reject
the null hypothesis H 0, indicating that sodium intake is a significant predictor of
blood pressure.

6. Predicted blood pressure for a sodium intake of 6.3:

For a sodium intake of 6.3, the predicted blood pressure is approximately
148.46.

These results suggest a significant positive linear relationship between sodium intake
and blood pressure, and we can use sodium intake to predict blood pressure with
reasonable accuracy.
Temperature (C 0 ¿ MilkShake Sales (Peso)
(X) (Y)
14.2 215
16.4 325
11.9 180
 15.2 300
18.5 400
22.1 500
19.4 400
25.1 610
23.4 520
18.1 400
22.6 430
17.2 410
5. A local shop of milk shakes keeps a track of the amount of milkshakes they
sell in accordance to the temperature on that day. Below are the figures of their
sale and temperature for the last 12 days. Comment on the relationship.

To analyze the relationship between temperature and milkshake sales, we can

calculate the Pearson correlation coefficient and develop a linear regression model.
1. Compute the Pearson correlation coefficient (r) to determine the strength and
direction of the relationship between temperature and milkshake sales.

2. Calculate the regression equation for predicting milkshake sales based on

temperature. This involves determining the slope and intercept of the
regression line.

3. Interpret the results: We can use the correlation coefficient to assess the
strength of the relationship, and the regression equation will allow us to predict
milkshake sales given a specific temperature.

Let’s proceed with these calculations.

Here are the results for the relationship between temperature and milkshake sales.
1. Pearson correlation coefficient (r):
r =0.957, which indicates a very strong positive correlation between
temperature and milkshake sales. As temperature increases, milkshake sales
also tend to increase.

2. Coefficient of determination (r 2):

2
r =0.916 This means that approximately 91.6% of the variance in milkshake
sales can be explained by the temperature.

3. Regression equation:
The regression equation is:
Y^ =−157.68+29.37 · X

where Y^ is the predicted milkshake sales, and X is the temperature in ℃ .

This analysis shows a strong positive relationship between temperature and

milkshake sales, suggesting that higher temperatures lead to increased sales of
milkshakes.