VI

F-Test

F-TEST (ONE-WAY ANALYSIS OF VARIANCE)

It is used if:
1. We are comparing two or more independent groups
2. The data is normally distributed
3. The data are interval and ratio data
4. There is only one variable involved
5. We want to find out if there is significant difference between and among the means of the groups

ANOVA Table:

Degrees of Freedom Sum of Squares Mean Squares F-Value

Sources of Variation
df SS MS Computed Tabular
(∑ xn )2 BSS
Between Groups 𝑑𝑓b = K − 1 BSS = ∑ [ ] − CF MSB =
n 𝑑𝑓b

MSB
WSS F=
Within Group 𝑑𝑓w = (N − 1) − (K − 1) WSS = TSS − BSS MSW = MSW
𝑑𝑓W

Total 𝑑𝑓T = 𝑁 − 1 𝑇𝑆𝑆 = [∑(x 2 )] − CF -

(∑ x)2
Note: Correction Factor (CF) = ∑n

Example 1:
A sari-sari store is selling 4 brands of shampoo. The owner is interested if there is a significant difference in the
average sales of the four brands of shampoo for one week. The following data are recorded. Perform a test to show if the
average sales of the four brands of shampoos are equal. Use 0.05 level of significance.
BRAND
A B C D
7 9 2 4
3 8 3 5
5 8 4 7
6 7 5 8
9 6 6 3
4 9 4 4
3 10 2 5

Solution:
1. State the problem: Is the average sales of the four brands of shampoos equal?
2. Formulate the null and alternative hypotheses:
Ho: x̅1 = x̅2 = x̅3 = x̅4
Ha: x̅1 ≠ x̅2 ≠ x̅3 ≠ x̅4
3. Set the level of significance and solve for other parameters:
α = 0.05
df1 = k-1 = 4-1 = 3
df2 = N-k = 28-4 = 24
tabular value = 3.01
4. Compute for the test statistic:
BRAND
A B C D A2 B2 C2 D2
7 9 2 4 49 81 4 16
3 8 3 5 9 64 9 25
5 8 4 7 25 64 16 49
6 7 5 8 36 49 25 64
9 6 6 3 81 36 36 9
4 9 4 4 16 81 16 16
3 10 2 5 9 100 4 25
∑xA = 37 ∑xB= 57 ∑xC= 26 ∑xD= 36 SSA = 225 SSB = 475 SSC = 110 SSD = 204
*summary of sums and squares
 To compute for Total SS: (Sum of Squares)
∑ x = 37 + 57 + 26 + 36 = 156 (add A+B+C+D+E……)
∑ x 2 = 225 + 475 + 110 + 204 = 1014 (add SSA +SSB…_
(∑ x)2 (156)2
TSS = ∑ x 2 − = 1014 − = 144.86
N 28
To compute for BSS: (between)
372 + 572 + 262 + 362 (156)2
BSS = − = 941.42 − 869.14 = 72.28
7 28
To compute for WSS: (within)
WSS = TSS − BSS = 144.86 − 72.28 = 72.58
To compute for MSB: (mean square between)
BSS 72.28
MSB = = = 24.09
𝑑𝑓1 3
To compute for MSW: (mean square within)

WSS 72.58
MSW = = = 3.02
𝑑𝑓2 24
The F-value then is:
MSB 24.09
= = 7.98
MSW 3.02

Degrees of Freedom F-Value

Sources of Variation Sum of Squares Mean Squares
df Computed Tabular
Brands of Shampoo 3 72.28 24.09
Error 24 72.58 3.02 7.98 3.01
Total 27 144.86 -
*table of summary
5. State the decision rule.
If the f-computed value falls in the critical region, we reject Ho.

-3.01 +3.01 7.98

6. Compare the computed value with its corresponding tabular value, then state your conclusion
Since the computed value 7.98 falls in the critical region, we reject Ho. The alternative hypothesis is accepted.
Conclusion: There is sufficient evidence to show that the average sales of the four brands of shampoos are not
equal (meaning there is a difference).

Analysis: This means that there are brands more preferred by the customers. Domingo (2011) states that the
choice of customers is based on the price of the shampoo.

The disadvantage of ANOVA is you cannot pinpoint which caused the difference.
The advantage is it is easier to solve.

A vs B -no difference

B vs C – there is a difference

C vs D - no difference

A vs C - no difference

A vs D - no difference
 BRAND
A B C D A2 B2 C2 D2
7 9 2 4 49 81 4 16
3 8 3 5 9 64 9 25
5 8 4 7 25 64 16 49
6 7 5 8 36 49 25 64
9 6 6 3 81 36 36 9
4 9 4 4 16 81 16 16
3 10 2 5 9 100 4 25
∑xA = 37 ∑xB= 57 ∑xC= 26 ∑xD= 36 SSA = 225 SSB = 475 SSC = 110 SSD = 204

SCHEFFÉ’S TEST (POST HOC TEST)

The F-test tells us that there is a significant difference in the average sales of the four brands of shampoos but as
to where the difference lies, it has to be tested further by Scheffé test.

Formula:
(x̅1 − x̅2 )2 where: F′ = Scheffé’s Test value
F′ = x̅1 = mean of sample 1
WSS(n1 +n2 )
n1 n2
x̅2 = mean of sample 2
n1 = size of sample 1
Solution: n1 = size of sample 2
A vs. B WSS = Within Mean Square
(x̅1 − x̅2 )2 (5.28 − 8.14)2
F ′ = MSW(n +n ) = 3.02(7+7)
= 9.51
1 2
n1 n2 (7)(7)
A vs. C
(5.28 − 3.71)2
F′ = 3.02(7+7)
= 2.87
(7)(7)

B vs. C
(8.14 − 3.71)2
F′ = 3.02(7+7)
= 22.82
(7)(7)

A vs. D
(5.28 − 5.14)2
F′ = 3.02(7+7)
= 0.02
(7)(7)
B vs. D
(8.14 − 5.14)2
F′ = 3.02(7+7)
= 10.46
(7)(7)
C vs. D
(3.71 − 5.14)2
F′ = 3.02(7+7)
= 2.38
(7)(7)

Comparison of the Average Sales of the Four Brands of Shampoo

Between F’ F table Interpretation
Brand (Fcrit0.05)(K-1)
A vs B 9.51 (3.01*3)=9.03 Significant
A vs C 2.87 9.03 Not significant
A vs D 0.02 9.03 Not significant
B vs C 22.82 9.03 Significant
B vs D 10.46 9.03 Significant
C vs D 2.38 9.03 Not significant

The table shows that there is a significant difference in the sales between brand A and brand B, brand B and brand
C and also brand B and brand D. However, brands A and C, A and D, and C and D do not significantly differ in their
average sales.
This implies that brand B is more saleable than brands A, C, and D.
F-TEST (TWO-WAY ANALYSIS OF VARIANCE with interaction effect)
It is used if:
1. We are comparing two or more variables
2. The data is normally distributed
3. The data are interval and ratio data
4. We want to find out if there is an interaction effect between the variables

ANOVA Table:

Mean F-Value
Sources of Sum of Squares Degrees of Freedom
Squares Interpretation
Variation SS Df Computed Tabular
MS

Between ∑(∑ xc )2 SSc MSc

SSc = N
− CF 𝑑𝑓c = c − 1 MSc = Fc =
Columns 𝑑𝑓c MSW
c

Between ∑(∑ xr )2 SSr MSr

SSr = N
− CF 𝑑𝑓r = r − 1 MSr = Fr =
Rows 𝑑𝑓r MSW
r

SScr MScr
Interaction SScr = SST − SSW −SSr − SSc 𝑑𝑓cr = (𝑐 − 1)(𝑟 − 1) MScr = Fcr =
𝑑𝑓cr MSW

Within (∑ xn )2 SSW
SSW = [∑(x 2 )] − ∑ 𝑑𝑓w = K(n − 1) MSW = - - -
Group n 𝑑𝑓W

Total SST = [∑(x 2 )] − CF 𝑑𝑓T = N − 1 - - - -

(∑ x)2
Note: Correction Factor (CF) = and K = c × r
∑n

Example:
Forty-five language students were randomly assigned to one of three instructors and to one of the three methods of
teaching then achievement was measured on a test administered at the end of the term. Use the two-way ANOVA with
interaction effect at 0.05 level of significance to test the following hypotheses:
TEACHER FACTOR
A B C
40 50 40
Teaching 1
Method of

41 50 41
40 48 40
39 48 38
38 45 38
40 45 50
Teaching 2
Method of

41 42 46
39 42 43
38 41 43
38 40 42
40 40 40
Teaching 3
Method of

43 45 41
41 44 41
39 44 39
38 43 38
Solution:
1. Statement of the Problem:
1. Is there a significant difference in the performance of the three groups of students under three different
instructors?
2. Is there a significant difference in the performance of the three groups of students under three different methods
of teaching?
3. Is there an interaction effect between teacher and method of teaching factors?
2. Hypotheses:
1. Ho: There is no significant difference in the performance of the three groups of students under three different
instructors.
H1: There is a significant difference in the performance of the three groups of students under three different
instructors.
2. Ho: There is no significant difference in the performance of the three groups of students under three different
methods of teaching.
H2: There is a significant difference in the performance of the three groups of students under three different
methods of teaching.
 3. Ho: Interaction effects are not present.
H3: Interaction effects are present.
3. Level of Significance:
α = 0.05
dfT = N-1 = 45 – 1 = 44
dfW = k(n-1) = 9(5 – 1) = 9(4) = 36
dfc = c-1 = 3 – 1 = 2 (column)
dfr = r-1 = 3 – 1 = 2 (row)
dfcr = (c-1)(r-1) = (3-1)(3-1) = (2)(2) = 4
4. Statistics : F-Test Two-Way ANOVA with interaction effect

TEACHER FACTOR
A B C
Teaching 1 40 50 40
Method of

41 50 41
40 48 40
39 48 38
38 45 38
Total 198 241 197 636
40 45 50
Teaching 2
Method of

41 42 46
39 42 43
38 41 43
38 40 42
Total 196 210 224 630
40 40 40
Teaching 3
Method of

43 45 41
41 44 41
39 44 39
38 43 38
Total 201 216 199 616
Total of Totals 595 667 620 GT=1882

Correction Factor
(∑ x)2 (1,882)2 3,541,924
CF = ∑n
= = = 78,709.42
45 45
Sum of Squares
SST = ∑ x 2 − CF = 402 + 412 + ⋯ + 392 + 382 − 78,709.42 = 79,218 − 78,709.42 = 508.58
(∑ xn )2 1982 1962 2012 2412 2102 2162 1972 2242 1992
SSW = ∑ x 2 − ∑ = 79,218 − ( + + + + + + + + ) = 129.2
n 5 5 5 5 5 5 5 5 5
∑(∑ xc )2 5952 + 6672 + 6202
SSc = N
− CF = − 78,709.42 = 78,887.6 − 78,709.42 = 178.18
15
3
∑(∑ xr )2 6362 + 6302 + 6162
SSr = N
− CF = − 78,709.42 = 78,723.47 − 78,709.42 = 14.05
15
3
SScr = SST − SSW −SSr − SSc = 508.58 − 129.2 − 178.18 − 14.05 = 187.15
Mean Sum of Squares
SSc 178.18
MSc = = = 89.09
𝑑𝑓𝑐 2
SSr 14.05
MSr = = = 7.02
𝑑𝑓𝑟 2
SScr 187.15
MScr = = = 46.79
𝑑𝑓𝑐𝑟 4
SSW 129.20
MSW = = = 3.59
𝑑𝑓W 36
F-value computed
MSc 89.09
Fc = = = 24.82
MSW 3.59
MSr 7.02
Fr = = = 1.95
MSW 3.59
MScr 46.79
Fcr = = = 13.03
MSW 3.59
 ANOVA TABLE
Sum of Squares Degrees of Freedom Mean Squares F-Value
Sources of Variation Interpretation
SS Df MS Computed Tabular
Between Columns 178.18 dfc=2 89.09 24.82 3.26 S
Between Rows 14.05 dfr =2 7.02 1.95 3.26 NS
Interaction 187.15 dfcr=4 46.79 13.03 2.63 S
Within Group 129.20 dfw=36 3.59 - - -
Total 508.58 44 - - - -

5. Decision Rule:
If the computed f-value is greater than the F critical/tabular value, disconfirm H o.
6. Conclusion:
With the computed F-value (column) of 24.82 compared to the F-tabular value of 3.26 at 0.05 level of
significance with 2 and 36 degrees of freedom, the null hypothesis is disconfirmed in favor of the research
hypothesis which means that there is a significant difference in the performance of the three groups of students
under three different instructors. It implies that instructor B is better than instructor A.
With regard to the F-value (row) of 1.95, it is lesser than the F-tabular value of 3.26 at 0.05 level of
significance with 2 and 36 degrees of freedom. Hence, the null hypothesis of no significant differences in the
performance of the students under the three different methods of teaching is confirmed.
However, the F-value (interaction) of 13.03 is greater than the F-tabular value of 2.63 at 0.05 level of
significance with 4 and 36 degrees of freedom. Thus, the research hypothesis is confirmed which means that
interaction effect is present between the instructors and their methods of teaching. Students under instructor B
have better performance under methods of teaching 1 and 3 while students under instructor C have better
performance under method 2.