Comparison of non-users and users of self-checkout counters in Singapore's retail industry

This research compares non-users and users of self-checkout counters in Singapore's retail industry. It includes a case study on Amazon and covers descriptive statistics, hypothesis tests, and the concept of p-value.

Business Research quantitative research

TABLE OF CONTENTS
PART 1............................................................................................................................................3
1. Aim & research questions........................................................................................................3
2.a. Instrument for carrying out survey.......................................................................................3
b. Concept on which instrument measured..................................................................................3
c. Cronbach alpha coefficient......................................................................................................4
3.Collection of Data.....................................................................................................................4
4. Findings...................................................................................................................................4
5. Conclusion & further investigation.........................................................................................5
PART - 2..........................................................................................................................................5
Case study - 1: Amazon...............................................................................................................5
1. Frequency table........................................................................................................................5
2. Hypothesis test for RQ1...........................................................................................................5
3. Hypothesis test for RQ2...........................................................................................................5
4. Reason for conducting hypothesis test....................................................................................6
Cast study 2..................................................................................................................................6
1. Descriptive statistics................................................................................................................6
2. Independent t test.....................................................................................................................6
3. Anova test................................................................................................................................6
4. Concept of p value in hypothesis.............................................................................................7
REFERENCES................................................................................................................................8
APPENDIX......................................................................................................................................9

PART 1
1. Aim & research questions
The purpose of the research is to compare how the non-users & users of self-checkout
counters differ with respect to the retail industry of Singapore.
The research questions are:
Q1: Is there any demographic difference among non-users & users of self-checkout counters or
SCC?
Q2: What perceptual differences lies among the non-users & users of SCC with regards to the
features of SCC in Singapore which involves fun, complexity, relative advantage, compatibility
and reliability?
Q3: What differences lies in terms of situational factors that are supposed to be affecting the
intention of non-users and users of SCC while using terminals?
2.a. Instrument for carrying out survey
The chosen instrument for survey consists of three section which include:
 Demographic information that include age, gender and educational qualification
 Five point Likert scale questions that identify the reliability in order to measure the
respondent’s point of view related to SCC.
 Seven point likert scale questions that help to determine the probability of using SCC in
different situation.
b. Concept on which instrument measured
The name of the second section is 5 point Likert scale questionnaire that help would be
helpful in determining the perception of SCC. In this different dimension used which include
perceived complexity, fun, relative advantage & reliability measured that will further measure by
three item scale adapted. Next, compatibility of SCC which a respondent’s lifestyle by using the
framework given by Roger. Therefore, it can be stated that there are different factors which need
to be used in order to provide valid outcome.

c. Cronbach alpha coefficient
Cronbach 𝛼 coefficients are the most common test score reliability that is used to
determine whether the values provide a valid outcome. Therefore, it is important for the present
paper to conduct the test in order to identify how closely related a set of item as a group so that it
assist to examine the accurate results. In accordance with the article, it has been identified that
the alpha coefficients for Perceived complexity, Fun, Relative Advantage & Reliability were
0.84, 0.92, 0.85 & 0.72 respectively that entails that it provides the valid outcome because the
dataset are closely linked with each other and provide valid outcome as well.
3.Collection of Data
Non-probability sampling method has been used by the company which focuses on
gaining information from participants. Random sampling method has not been used for the
present study whereas, scholar uses convenience sampling method that helps to provide proper
information pertaining to the same (Şahin and Aybek, 2019). The responses are selected by using
convenience sampling and that is why, sample are selected easily.
4. Findings
a)
In order to determine the association between the demographic information, chi-square
test has been applied which entails no relationship between use of SCC & gender because the
identified value of p is greater than 0.05. Therefore, it indicates that null hypothesis must be
accepted and accordingly it has been determined that there is no statistical difference in the use
of SCC with different demographic segments.
b)
The 4 in p value indicated that there is only 40% association between the age and
education. It has calculated by applying chi-square test in SPSS.
c)

The rationale of getting all the test results statistically significant with a moderate effect
sizes is due to Cohen’s d that provide the accurate results in all cases except independent sample
t test.
5. Conclusion & further investigation
The recent study in the research indicated that most of the study that already conducted in
the past years shows that there are several degrees to resistance. Also, it is probable that
consumers are well known with the service delivery & further develop preference for a service
encounter. On the other side, the further research will be carried out to evaluate whether there is
any difference among non-users of SCC & isolated strategies formulated with regard to
individual segments for non-users.
PART - 2
Case study - 1: Amazon
1. Frequency table
Through the table 1, it has been identified that 32 out of 87 respondents stated no, which
means they are not consider shopping at Amazon fresh whereas 55 of them stated that they use
Amazon for shopping.
2. Hypothesis test for RQ1
By applying binomial test under test 2, it has been identified that the in the case of people
who do not prefer to shopping at Amazon Fresh then the null hypothesis must be accepted over
other because the resulting p value is greater than 0.05. However, in case of people who stated
yes, analysed that there is an alternative hypothesis has accepted because the identified p value is
lower than 0.05.
3. Hypothesis test for RQ2
With the help of table 3, by applying chi-square test, it has been identified that the
alternative hypothesis must be accepted because the obtained value of p (0.02< 0.05) which
means that there is a statistical difference among those who are convenient with mobile
technology usually considered shopping at Amazon Fresh. Moreover, the value of phi/Cramer

shows that there is a lower association between the values and this indicated that it might
changes with 24% only when the value of independent changes.
4. Reason for conducting hypothesis test
The rationale for conducting hypothesis test over comparing sample statistics is such that
it helps to determine the views of different people towards shopping so that they can determine
whether they shop from the Amazon Fresh or not (Mishra and et.al., 2019). On the other side, if
sample statistics is only used that it helps to determine the central tendency but do not help to
determine which hypothesis is accepted over other.
Cast study 2
1. Descriptive statistics
Through table 4, it has been identified that from 134 respondents, 60 of them stated that
there is no entrepreneurship module and 74 of them stated that they receive an entrepreneurship
module. On the other side, the levene test for homogeneity reflected that there is null hypothesis
has accepted over other. That is why, it can be stated that there is no relationship between the
entrepreneurship intention score. Further, under normality test, it has been identified by using
Shapiro Wilk that the determined p value is more than 0.05 & that is why, null hypothesis must
be accepted and also, there are no differences among the 2 types of students, those who studied
for an entrepreneurship module & those who didn’t.
2. Independent t test
Through the table 5, it has been identified by applying independent sample t test there is
an alternative hypothesis is accepted over other because the value of p shown in the table
reflected that it is 0.009 which is less than the set criteria that is, 0.05. So, it can be said that the
average score for an entrepreneurship intention are significantly different.
3. Anova test

Through the above, it has been identified that the resulting p value is more than the
standard criteria and that is why, it can be stated that there is no effect on the average score for
entrepreneurship intention. Also, the levene’s test is also stated that there is no difference
between the values because the identified p value is higher than the 0.05. Accordingly, the null
hypothesis would be accepted which entails no difference between the values.
4. Concept of p value in hypothesis
The p value is referred to probability value and it identify how probably the data could
have occurred under the null hypothesis and it determine the calculating the likelihood the test
statistics. It is used for the data to validate a hypothesis against the observed value and its
limitation involve that p value ignore whether the selected test was appropriate or not (Ioannidis,
2018). Along with this, it is depend upon the sample size and do not indicate causality within a
dataset.

REFERENCES
Books and Journals
Ioannidis, J. P., 2018. The proposal to lower P value thresholds to. 005. Jama. 319(14). pp.1429-
1430.
Mishra, P. and et.al., 2019. Descriptive statistics and normality tests for statistical data. Annals of
cardiac anaesthesia. 22(1). p.67.
Şahin, M. D. and Aybek, E. C., 2019. Jamovi: an easy to use statistical software for the social
scientists. International Journal of Assessment Tools in Education. 6(4). pp.670-692.

APPENDIX
Table 1: Frequency statistics
Table 2: hypothesis test for RQ1
Table 3: Hypothesis test for RQ2

Table 4: Descriptive statistics

Table 5: Independent sample t test
Table 6: Anova test