The data collected from the questionnaire survey were
analyzed using Excel and IBM SPSS Statistics version 25.0. Descriptive
statistics were employed to gain insights from the responses. In terms of
respondent gender distribution, the majority (82.8%) were male, with female
respondents accounting for 17.2%. Regarding the distribution of respondents
based on their organizations, the largest group (39.4%) represented academic
institutions, while the smallest group (1.4%) was associated with the automobile
sector. These descriptive statistics provide a clear picture of the gender and
organizational diversity among the survey participants.
Variables and components
codes
All the variables and their components considered are
coded for the computational easiness. The codes and its meaning are as per the following
(Table 1).
Reliability analysis
For the reliability analysis, the Cranach’s alpha
value is calculated. The overall Cronbach’s alpha value is summarized in table
below (Table 2). Factors are acceptable if the value of alpha is greater than
0.7. Here, in the above table, we see that the Cronbach’s alpha calculated is
0.864. It means, all the factors are acceptable. The result shows that the
internal uniformity of questionnaire is good and strength of association is
also good. The reliability test is done for each variable also. The Cronbach’s
alpha value for each variable is summarized in below table. From the above
table, the alpha value of each variable is greater than 0.7 which means that
all the factors are acceptable. Similarly, the alpha value for all items is
0.921 (greater than 0.7), hence all the items considered are consistent and
acceptable (Table 3).
Kaiser-Meyer-Olkin
measure of sampling adequacy for acceptance of parameters
This measure varies between 0 and 1, and values closer
to 1 are better. A value of 0.6 is suggested minimum. For this research value
obtained is 0.909 as shown in table below (see table 9) which is closer to 1
i.e. the research accepts entire success factors and barriers for the study
(Table 4).
Bartlett’s test of
sphericity
This tests the null hypothesis that the correlation
matrix is an identity matrix. An identity matrix is matrix in which all of the
diagonal elements are 1 and all off diagonal elements are 0. Small values less
than 0.05 of the significance level indicate factor analysis is useful for the
collected data. From the table 9, the significance level has low value than
0.005 and the factor analysis is useful for the collected data. The p-value is
0.000 (less than 0.05) which indicates that the factor loading is justified.
Principal component
analysis for categorization of factors
PCA is used as a data analysis tool for making
predictive models. It visualizes genetic distance and relatedness between
populations. PCA can be done by eigen value decomposition of a data covariance
(or correlation) matrix. Principal Component Analysis (PCA) is the process of
data reduction or dimension reduction. For this research PCA is done through
SPSS. From the factor analysis the data is converted into six principal
components as shown in below (Table 5). The different factors are categorized
in same components (factor loading) for those factors having significant factor
loading value greater than 0.3 (Table 6).
Total variance explained
(TVE)
The % of Variance column gives the ratio, expressed as
a percentage, of the variance accounted for each component to the total
variance in all of the variables. The first component will always have the
highest variance (and hence have the highest eigenvalue), and the next
component will have as much of the left over variance as it can, and so on.
Hence, each successive component will account for less and less variance. The
result obtained for this study can be seen in table 6 below:
Varimax rotation
A varimax rotation simplifies the expression of a
particular sub-space in terms of few major items. The actual coordinate system
is unchanged. The alignment is on the basis of orthogonally. Varimax maximizes
the sum of the variances of the squared loadings (squared correlations between
variables and factors). All the coefficient will be either large or near zero,
with few intermediate values.
Naming of components
Looking for similarity between items that load on a
factor, the first component is named as “Component Related to Management and
Leadership” that contributes about 33.52 % of the total variance explained. The
second component is named as “Component Related to Internal Barriers” that
contributes about 9.39% of the total variance explained. The third component is
“Component Related to Security Concern” that contributes about 4.33% of TVE.
The fourth component is “Component Related to External Barrier” that
contributes about 3.93% of TVE. The fifth component is “Component Related to
Cost” which contributes about 3.81% of TVE. Lastly, the sixth component is
“Component Related to Policy” which contributes about 3.57% (Table 7) of TVE.
The Eigen value of the six different components categorized using PCA and
Varimax are seen to be greater than 1 (Table 8). It describes that all these
components or factors are highly reliable. Moreover, the different factors are
categorized in same components (factor loading) for those factors having
significant factor loading value greater than 0.3.