4.

DATA ANALYSIS

4.1Introduction

The chapter then moves on to explain the results of the data analysis. Methods for analyzing
survey data are provided below after the data have been imported into IBM SPSS Statistics 25.
(A statistical software tool). Both descriptive and inferential statistics are covered in this section,
as they are the backbone of the field. The relevant dataset has been subjected to both reliability
analysis and logistic regression, two inferential statistical processes, with the same outcome. In
data analysis, descriptive statistics are employed to offer information in a relevant and
comprehensible style for the reader.

4.2Demographic Factor Analysis

4.2.1 Gender

Table 1 Gender

Indicate your Gender

Frequency Percent Valid Percent Cumulative Percent

Valid Female 99 49.5 49.5 49.5

Male 101 50.5 50.5 100.0

Total 200 100.0 100.0

 Figure 1: Gender

Male respondents made up 50.5% of the total sample size, as shown by the finding that 101
people (or so) in the surveyed population explicitly identified as such. The remaining 49.5%
consisted of opinions from 99 different women who took part in the study. Every individual has
made an argument for their gender, and these must be taken into account.

4.2.2 Age Group

Table 2 Age

Which age, bracket do you fall in?

Frequency Percent Valid Percent Cumulative Percent

Valid 20 – 25 years 31 15.5 15.5 15.5

26 – 30 years 43 21.5 21.5 37.0

31 – 35 years 49 24.5 24.5 61.5

36 – 40 years 44 22.0 22.0 83.5

41 years & above 33 16.5 16.5 100.0

Total 200 100.0 100.0

 Figure 2: Age

In the table above, you can see how the ages of the sampled population are distributed. Twenty-
five percent (24.5%) of respondents fell in the 31–35 age range. Only 15.5% of the sample
consisted of people between the ages of 20 and 25.

4.2.3 Education Level

Table 3 Education Level

Which level of education did you attain?

Frequency Percent Valid Percent Cumulative Percent

Valid Degree level 88 44.0 44.0 44.0

Diploma level 17 8.5 8.5 52.5

Higher Diploma 25 12.5 12.5 65.0

Masters level 36 18.0 18.0 83.0

Others 34 17.0 17.0 100.0

Total 200 100.0 100.0

 Figure 3: Education Level

Looking at Table 03, we can see that the percentage of people who have a degree makes up 44%
of the entire data set. In contrast, the majority of those who participated (8.5% of the total)
reported having at least a Diploma level of schooling. In addition, data showed that 12.5% of
participants held a Higher Diploma as their highest level of education attainment. This was seen
despite the fact that many of the participants held master’s degrees. The situation described
above is, in fact, accurate, as further investigation has shown.

4.2.4 Experience

Table 4 Experience

For how long have you been working in this organization?

Frequency Percent Valid Percent Cumulative Percent

Valid 11 year & above 11 5.5 5.5 5.5

3 – 5 years 73 36.5 36.5 42.0

6 – 10 years 47 23.5 23.5 65.5

Below 2 years 69 34.5 34.5 100.0

Total 200 100.0 100.0

 Figure 4: Experience

Table 04 shows that the largest percentage of the sample (35%) consists of people who have
either participated in the study or have experience in the field for between three and five years.

4.2.5 Term of Service

Table 5 Term of Service

Indicate your terms of service

Frequency Percent Valid Percent Cumulative Percent

Valid Casual 2 1.0 1.0 1.0

Contract terms 22 11.0 11.0 12.0

Permanent 161 80.5 80.5 92.5

Temporary 15 7.5 7.5 100.0

Total 200 100.0 100.0

Figure 5: Term of Service

According to Table 05, only 2% of the population is classified as having a casual term of
employment, whereas the vast majority, or 80.5%, classify themselves as having a permanent
term of service. The reason for this is because 80.5% of the population has a term of service. It
was also discovered that 11% of the sample population met the criteria set forth in the
agreement. It was determined through subsequent research that this was in fact the case.

4.2.6 Faced Challenges

Table 6 Faced Challenges

Do you face any challenges in implementing e-procurement in your organization?

Frequency Percent Valid Percent Cumulative Percent

Valid No 2 1.0 1.0 1.0

Yes 198 99.0 99.0 100.0

Total 200 100.0 100.0

Figure 6: Faced Challenges

Table 06 demonstrates that a whopping 99% of Colombo-based personnel have been properly
registered.
 4.2.7 Cost associated challenges

Table 7 Cost associated challenges

If Yes, which of the following are likely to be your cost associated challenges

Frequency Percent Valid Percent Cumulative Percent

Valid Acquisition of softw 8 4.0 4.0 4.0

Budget for compute 147 73.5 73.5 78.0

Budget for computer 14 7.0 7.0 85.0

Maintenance of equip 7 3.5 3.5 88.5

Training of staff 23 11.5 11.5 100.0

Total 200 100.0 100.0

Figure 7: Cost associated challenges

Table 07 shows that the largest share of the sample consists of participants who are experiencing
difficulties with their computing budgets. In addition, around 4% of the sample group was
determined to fall within the Acquisition of softw. This was a subset of the total scope of this
spectrum. It was determined through subsequent research that this was in fact the case.
 4.3Reliability Analysis

A reliability analysis, in which the consistency of the data collected is evaluated, is a crucial
aspect of every study. The findings demonstrate that reliability analysis is a valuable tool for
evaluating a scale because it reveals hidden relationships between factors. Cronbach's alpha is a
reliability coefficient that can be calculated as part of a larger analysis. This number represents
how stable the situation currently is. The dependability of a survey can be measured by using a
statistic called Cronbach's alpha. If the dependability coefficient of a sample is larger than 0.7,
then the sample can be regarded statistically significant.

Table 8 Summary of Reliability Analysis of Variables

Variable Cronbach’s Alpha Reliability Result

Supplier enablement status 0.993 Reliable (0.993 > 0.7)
System security 0.968 Reliable (0.968 > 0.7)
Cost Implications 0.971 Reliable (0.971 > 0.7)
Legal Infrastructure 0.950 Reliable (0.950 > 0.7)
Implementation of e-procurement. 0.969 Reliable (0.969 > 0.7)

After achieving the target Cronbach's Alpha, it was decided to end the trial in accordance with
the predetermined protocol. SPSS was used to determine whether or not the provided questions
for each variable had an alpha value greater than 0.7. The analysis showed that the queries were
analytically sound enough to meet this criterion. The second piece of information was that
standards were met. The study's dependability focus was ensured by the researcher's careful
question selection.

4.4Correlation Analysis

The correlation coefficient is a statistical tool for gauging the degree to which two variables are
related to one another. The strength of the relationship between the two factors will determine
how much weight this figure carries. Correlation coefficient calculations were the inspiration for
this statistical tool. As a way to measure the closeness of a relationship between two variables,
the term "correlation coefficient" was coined by statisticians. It is also believed that this same
individual conceptualized the term. This form of measurement is typically referred to by the
name Pearson's product-moment correlation coefficient. When there are multiple continuous
variables in a study, the Pearson product-moment correlation is calculated by dividing the
correlation coefficient by the total number of continuous variables.

We can evaluate the significance of zero-variable relationships by comparing the correlation

coefficients r and r0. There is no evidence that these two variables are related, as there is no
correlation between them. Neither of these things seems to have any bearing on the other.
Examining correlations is necessary for making comparisons only when the two variables in
question have a linear connection. Even if there is no correlation coefficient between two
variables, a nonlinear relationship may still exist.

Table 9 Correlation Analysis of Dependent and Independent Variables

Correlations

Supplier_enabl System_securit Cost_Implicatio Legal_Infrastru Implementating

ement_status y ns cture _eprocurement

Supplier_enablement_stat Pearson Correlation 1 .901** .855** .913** .800**

us
Sig. (2-tailed) .000 .000 .000 .000

N 200 200 200 200 200

System_security Pearson Correlation .901** 1 .873** .879** .814**

Sig. (2-tailed) .000 .000 .000 .000

N 200 200 200 200 200

Cost_Implications Pearson Correlation .855** .873** 1 .839** .870**

Sig. (2-tailed) .000 .000 .000 .000

N 200 200 200 200 200

Legal_Infrastructure Pearson Correlation .913** .879** .839** 1 .826**

Sig. (2-tailed) .000 .000 .000 .000

N 200 200 200 200 200

Implementating_eprocure Pearson Correlation .800** .814** .870** .826** 1

ment Sig. (2-tailed) .000 .000 .000 .000

N 200 200 200 200 200

**. Correlation is significant at the 0.01 level (2-tailed).

In the table below, we give a synthesis of the findings from the correlation study. It's not hard to
see that the two groups of numbers in the table are connected.

Supplier enablement status, System security, Cost Implications, Legal Infrastructure, and
Implementing e-procurement are all independent factors that might have a notable impact on the
dependent variable, which is the implementation of e-procurement. Given that the Pearson
correlation between the cost implication and the Implementing e-procurement is 0.870, we may
infer that there is a strong positive association between the two. The lowest level of correlation
was found between the criterion "Supplier enablement status" and the other three measures
(Pearson Correlation = 0.800). Despite this, the other three elements are directly related to one
another.

4.5Regression Analysis

Table 10 Variable Entered/Removed

Variables Entered/Removedb

Model Variables Entered Variables Removed Method

1
Legal_Infrastructure,
Cost_Implications,
System_security, . Enter
Supplier_enablement_
statusa

a. All requested variables entered.

b. Dependent Variable: Implementating_eprocurement

Table 11 Model Summary

Model Summary

Std. Error of the

Model R R Square Adjusted R Square Estimate

1 .888a .789 .785 .33412

a. Predictors: (Constant), Legal_Infrastructure, Cost_Implications,

System_security, Supplier_enablement_status

Table 11 of the Model Summary displays an R-squared value of 0.789 and an adjusted R-squared
value of 0.785. According to these calculations, there are just 21 independent variables left. The
fact that the tabled R-Squared value is larger than 50% indicates that the developed theoretical
framework can be considered a reliable model.

Table 12 ANOVA
ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 81.511 4 20.378 182.538 .000a

Residual 21.769 195 .112

Total 103.280 199

a. Predictors: (Constant), Legal_Infrastructure, Cost_Implications, System_security,

Supplier_enablement_status

b. Dependent Variable: Implementating_eprocurement

The number 0.000 was found to be statistically significant when compared to zero in the analysis
of variance results table. This value emphasizes that after a particular point in time, a model
needs to have a significance level of 0.005 or lower in order to be regarded trustworthy. In
addition, the fact that this value was found despite having a significance value of less than 0.005
is supportive of the validity of the model.
Table 13: Regression Coefficients

Coefficientsa

Standardized
Unstandardized Coefficients Coefficients

Model B Std. Error Beta t Sig.

1 (Constant) .244 .157 1.553 .122

Supplier_enablement_status -.079 .090 -.084 -.882 .379

System_security .075 .089 .073 .839 .402

Cost_Implications .604 .074 .587 8.144 .000

Legal_Infrastructure .347 .086 .346 4.022 .000

a. Dependent Variable: Implementating_eprocurement

The results of the independent variables' multiple regression analysis are provided in Table 15.
This exemplifies the impact that various explanatory factors have on the variable of interest. All
of the independent variables are statistically significantly correlated with the dependent variable,
as shown by the prior correlation analysis. Therefore, the independent variables must have a
major bearing on the dependent one. As a result, we conducted a thorough analysis of all of the
factors involved. Results from the statistical analysis show that Supplier enablement status and
System security both have significance values over the commonly accepted threshold of 5%, at
0.379 and 0.402, respectively. This suggests that the Supplier enablement status and System
security variables do not significantly affect the outcome. However, the Cost Implications and
Legal Infrastructure variables have a significant effect on the independent variable.

4.6Chapter Summary

In order to achieve the research aims and objectives outlined in the introduction, the survey data
is analyzed and organized in this section. A database was developed after an initial database
concept was conceived and some investigation into demographic factors was conducted. A
reliability test of the questionnaire must be conducted to ensure the accuracy of each response.
The investigation proceeded to other areas after reliability tests were passed. The importance and
direction of variables could not be established without conducting a correlation analysis.
Similarly, we needed to use regression analysis to figure out what role each variable played. In
other words, doing correlation analysis helps the researcher figure out what factors are at play.
The significance of each variable is calculated independently by regression analysis. The
researcher ultimately reached a conclusion regarding how to perform experiments to test
theories. In the following section of this chapter, we will analyze the results and suggestions in
the context of the existing literature.