Factor Analysis

The KMO evaluates sampling adequacy (whether or not the replies provided with the sample are
adequate), which should be close to 0.5 for satisfactory factor analysis to occur. Kaiser (1974)
recommends 0.5 (number for KMO) as a bare minimum (acceptable), values between 0.7 and 0.8 as
good, and values beyond 0.9 as excellent. According to the table above, the KMO measure is 0.679,
which is somewhat higher than 0.5 and hence almost enough acceptable.

Another indicator of the strength of the association between variables is Bartlett's test. The null
hypothesis that the correlation matrix is an identity matrix is tested here. An identity matrix is one in
which all diagonal elements are one and all off-diagonal elements are close to zero. You wish to dismiss
the null hypothesis. We can observe from the same table that Bartlett's Test Of Sphericity is important
(0.00). In other words, the significance level is less than 0.05. In fact, it is 0.00, indicating that the
significance level is low enough to reject the null hypothesis. As a result, the correlation matrix is not an
identity matrix.

Communalities
Initial Extraction
online influence 1.000 .464
branding pressures 1.000 .604
awareness 1.000 .357
ethical 1.000 .565
value orientated 1.000 .365
technology savvy 1.000 .266
seeking support for goods 1.000 .652
anti brand loyalty 1.000 .236
Extraction Method: Principal Component Analysis.

The table of communalities shows how much of the variance (i.e., the communality value which
should be more than 0.5 to be considered for further analysis. Else these variables are to be
removed from further steps factor analysis) in the variables has been accounted for by the
extracted factors. For instance, over 65.2% of the variance in “Seeking support for goods” is
accounted for, while 60.4% of the variance in “Branding Pressures” is accounted for.

Total Variance Explained

Extraction Sums of Squared
Initial Eigenvalues Loadings Rotation Sums of Squared Loadings
Compone % of Cumulative % of Cumulative % of Cumulative
nt Total Variance % Total Variance % Total Variance %
1 2.331 29.144 29.144 2.331 29.144 29.144 1.893 23.666 23.666
2 1.178 14.727 43.871 1.178 14.727 43.871 1.616 20.205 43.871
3 .979 12.233 56.103
4 .904 11.298 67.402
5 .856 10.701 78.102
6 .720 8.996 87.098
7 .567 7.082 94.181
8 .466 5.819 100.000
Extraction Method: Principal Component Analysis.
Eigenvalue actually reflects the number of extracted factors whose sum
should be equal to a number of items that are subjected to factor analysis.
The next item shows all the factors extractable from the analysis along
with their eigenvalues.
The Eigenvalue table has been divided into three sub-sections:

1. Initial Eigen Values

2. Extracted Sums of Squared Loadings

3. Rotation of Sums of Squared Loadings.

For analysis and interpretation purposes we are concerned only with Initial
Eigenvalues and Extracted Sums of Squared Loadings. As the requirement
for identifying the number of components or factors stated by selected
variables is the presence of eigenvalues to more than 1. Table herein
shows that for 1st component the value is 2.331 > 1, 2nd component is
1.178 > 1, 3rd component is 0.979 > 1, and 4th component is 0.904 < 1.
Thus, the stated set of 8 variables with 12 observations represent three
components. Further, the extracted sum of squared holding % of variance
depicts that the first factor accounts for 29.144% of the variance features
from the stated observations and the second 14.727%. Thus, 3 components
are effective enough in representing all the characteristics or components
highlighted by the stated 8 variables.

1. Component: As can be seen in the Communalities table 3 above,

there 8 components shown in column 1 under table 3.

2. Initial Eigenvalues Total: Total variance.

3. Initial Eigenvalues % of variance: The percent of variance

attributable to each factor.

4. Initial Eigenvalues Cumulative %: Cumulative variance of the

factor when added to the previous factors.

5. Extraction sums of Squared Loadings Total: Total variance after

extraction.

6. Extraction Sums of Squared Loadings % of variance: The percent

of variance attributable to each factor after extraction. This value is
of significance to us and therefore we determine in this step that they
are three factors which contribute towards why would someone by a
particular product.

7. Extraction Sums of Squared Cumulative %: Cumulative variance

of the factor when added to the previous factors after extraction.

8. Rotation of Sums of Squared Loadings Total: Total variance after

rotation.

9. Rotation of Sums of Squared Loadings % of variance: The

percent of variance attributable to each factor after rotation.

10. Rotation of Sums of Squared Loadings Cumulative

%: Cumulative variance of the factor when added to the previous
factors.
The scree plot is a graph of the eigenvalues against all the factors. The
graph is useful for determining how many factors to retain. The point of
interest is where the curve starts to flatten. It can be seen that the curve
begins to flatten between factors 3 and 4. Note also that factor 3 onwards
have an eigenvalue of less than 1, so only two factors have been retained.

Component Matrixa
Component
1 2
branding pressures .695
ethical .634 -.403
online influence .617
value orientated .595
awareness .503
technology savvy .464
anti brand loyalty .411
seeking support for goods .760
Extraction Method: Principal Component Analysis.
a. 2 components extracted.
Table above shows the loadings (extracted values of each item under 2
variables) of the eight variables on the two factors extracted. The higher
the absolute value of the loading, the more the factor contributes to the
variable. We have extracted two variables wherein the 8 items are divided
into 2 variables according to the most important items which similar
responses in component 1 and simultaneously in component 2. The gap
(empty spaces) on the table represents loadings that are less than 0.5, this
makes reading the table easier. We suppressed all loadings less than 0.5.
As the requirement of having precise computation of each factor
component, but Table depict that there is the presence of cross loading i.e.
one factor measuring more than one component. As this cross-loading is
very high in Table i.e. ethical have cross-loading, thus, for deriving more
adequate results, these cross-loadings need to be eliminated. For this, the
solution is to redistribute the factor loading by having rotation, and the
hence rotated component matrix is examined for identification of
components. 

Rotated Component Matrixa

Component
1 2
Ethical .748
online influence .664
Awareness .595
value orientated .533
seeking support for goods .766
branding pressures .702
technology savvy .463
anti brand loyalty .457
Extraction Method: Principal Component Analysis.
Rotation Method: Varimax with Kaiser Normalization.
a. Rotation converged in 3 iterations.
The idea of rotation is to reduce the number of factors on which the
variables under investigation have high loadings. Rotation does not
actually change anything but makes the interpretation of the analysis
easier. Looking at the table above, we can see that ethical and online
influence is substantially loaded on Factor (Component) 1 while seeking
support for goods and branding pressures are substantially loaded on
Factor 2. Sometimes the loading of variables is there on two components
or more. Therefore there is a requirement of checking the factor loading
value.
If the value is lower than the required value of 0.5 or the set limit (could be
0.6 too as per the researcher’s need of including the desired factor loading)
for one of the components, then that variable could be considered for
further analysis. But as the presence of more than 0.5 (or 0.6) loading in
more than one component represents that this variable represents two
components, thus, it is not effective in measuring a specific category.
Hence, need to be excluded. As in Table none of them have more than one
component, so they do not have to be excluded for further analysis. Hence,
further processing i.e., impact analysis or any other statistical analysis with
includes all variables can be done.
Component Transformation
Matrix
Component 1 2
1 .787 .616
2 -.616 .787
Extraction Method: Principal
Component Analysis.
Rotation Method: Varimax with Kaiser
Normalization.

T Test

Group Statistics
Gender N Mean Std. Deviation Std. Error Mean
component1 0 45 16.1870370370 1.86526560274 .278057378922
37037 9138 613
1 68 15.7561274509 2.19458270230 .266132243698
80383 2456 426
component2 0 45 13.0311111111 2.30708614157 .343920096167
11110 4793 263
1 68 13.5544117647 2.47804893302 .300507573421
05883 9046 409

Result and Conclusion

Independent Samples Test

Levene's Test for Equality
of Variances t-test for Equality of Means
95% Con
Sig. (2- Mean Std. Error of the
F Sig. t df tailed) Difference Difference Lower
component Equal variances 1.755 .188 1.083 111 .281 .430909586 .397846688 -.357450
1 assumed 056654 168022 56292

Equal variances not 1.120 104.144 .265 .430909586 .384892552 -.332334

assumed 056654 680968 85751

component Equal variances .381 .538 -1.129 111 .261 -.52330065 .463454634
2 assumed 3594772 275629 1.441666
02874
Equal variances not -1.146 98.954 .255 -.52330065 .456711981
assumed 3594772 703264 1.429521
91870
The various tests are performed using SPSS. In the KMO and Bartlett’s test, that evaluate
sampling adequacy, a KMO measure of 0.679 hints at it being almost acceptable. Even in the
Bartlett’s test that indicates strength of the association between variables, a value of 0.00 proves
that the correlation matrix is not an identity matrix.
Further, the table of communalities shows how much percentages of different variances is
accounted for. Next, in the table of total variance explained, the value of the 3 components,
‘Total’, ‘% of variance’ and ‘cumulative %’, effective enough in representing all the
characteristics or components later highlighted by the stated 8 variables.
Then, for the scree curve, between factors 3 and 4, it begins to flatten. Also, because factors 3
and onwards have eigenvalues less than 1, only two factors are kept. Moreover, the component
matrix shows that there is cross loading, i.e., one factor measuring more than one component
Because this cross-loading is quite high in Table, i.e., ethical have cross-loading, these cross-
loadings must be reduced in order to provide more adequate findings. For the rotated component
matrix table, none of the factors has more than one component, so they do not need to be
excluded for further investigation. As a result, further processing, such as impact analysis or any
other statistical analysis that covers all variables, is possible.