Business Research Methods - Importance of Self-Checkout System in Retail Sector

This report evaluates the importance of self-checkout system in the retail sector. It includes a study on differentiation between users and non-users of the system, demographic differences, and users’ evaluation of the technology aspect. The report also includes case studies on Amazon Fresh and Entrepreneurship Intention.

BUSINESS RESEARCH
METHODS

Table of Contents
PART-1............................................................................................................................................3
1...................................................................................................................................................3
2...................................................................................................................................................3
3...................................................................................................................................................4
4...................................................................................................................................................4
5...................................................................................................................................................4
PART-2............................................................................................................................................4
Case study-1: Amazon Fresh.......................................................................................................4
Case study-2 Entrepreneurship Intention.....................................................................................6
REFERENCES................................................................................................................................9
APPENDIX....................................................................................................................................10

PART-1
1.
The use of self-checkout system is getting higher accentuation in the retail sector. So with this
regard, in this report the key attention was paid on the prominence the system brings to the retail
sector. This is being used on wider scale in order to hike productive and mammoth customer
satisfaction, keeping the severity of the issue it has been taken into contemplation by the author.
The questions such as notching up differentiation between users and non-users of the system,
some other key questions such as demographic differences and changes they impart were
considered. At the end users’ evaluation of the technology aspect was also paid radical attention.
2.
A
The instrument was organized in the way suggested below-
 For self-checkout counters it was deciphered some prominent notion such as weather the
respondents was user of the undertaken system or not.
In the second section, Likert scale questions were taken into focus. With this regard five-point
scale was chosen keeping requirements of the research into mind (Chukhrova and Johannssen,
2021)
 The last one, used seven point Likert scale since this was intended to figure out likelihood
of such use so the scale got expanded. It this section the attention was paid that do such
users get guidance at shop in attempt to use this self-checkout system.
B
In this section the measurement process has been carried out to decipher the degree and direction
to which self-checkout counters were getting responded. With this regard, it was subdivided in
the factors below-
 Relative advantage
 Perceived complexity
 Reliability
 Fun
These all aspects got measured. At the same time this section also measured the compatibility
of self-checkout counters and how it was shaping up the life styles in Rogers framework.
C

The undertaken notion is quite useful since it helps to evaluate the reliability of the presented
study. The study or any form of research is only useful if it assures high level of reliability so
with this regard, both key conceptions such as data validity and reliability can be articulated
using the notion.
3.
“Convenience sampling” has been used as the data collection method in this particular research.
The higher quality and reliability can only be ensured if the collected data is appropriate for the
study so keeping the convictions in mind this technique has been used (Greenland, 2021)
4.
A
To make sure the tossed notion the author has given range of evidence so can substantiate its
logics with irrefutable arguments. For instance- it has presented the outcomes of undertaken test,
on the other hands the p- value was also presented. These tests and given scores suggested that
there was not difference.
B
The given figure 4 is here, stating that how many times the trial has been replicated. The given
equation is deciphering outcomes of Qui^2 tests and suggesting that the test has been applied
four times on the used data set.
C
The tests were statistically fulfilling all the requirements which was evaluating by checking the
criteria it has fulfilled. It was seen that the value of P was lower than 0.01 so it has fulfilled
statistical requirements. The value of P was= -9.10 so it is moderate since for being largely
affective it needs to be around 0.8 (Hameed, Chai and Rassau, 2020)
5.
In conclusion, it would be fair and rational to conclude that the undertaken system is having
great prominence to higher degree. It is quite essential and useful for the retail organizations in
order to be highly productive and handy. There have been multiple aspects so it is recommended
that further studies can be conducted in order to bring more intensive insights.
PART-2
Case study-1: Amazon Fresh
1

Form the conducted research and presented frequency table it can be articulated that a great or
significant portion of the participants are inclined to shop form Amazon Fresh. At the same time
around 36.8% of them has nodded in disagreement. Form their responses it was summarized that
they were reluctant to make purchase form Amazon Fresh (Rigner, 2019)
2
There has been two hypothesis taken into consideration. The null and alternative hypotheses
were as-
H0= The constellation of people prefers to make buy form the Amazon Fresh are not more than
50%
H1= The constellation of people prefers to buy form the company were more that 50%
From the intensive analysis it was found that the alternative hypothesis has been proven right. In
contrast the null hypotheses got rejected. The significance value was around 0.000 so it was
lower than the 0.05. here, it can be concluded that there are more than 50% participants has
nodded favouring the notion to make buy form Amazon Fresh.
3
H0= The difference between different proportion of people was not existing among people who
consider to make buy at Amazon Fresh and people who are firmed with the use of mobile
technology or are not using.
H1= The difference is existing among them.
Here, again the alternate hypothesis was proven right which nullified presence of null
hypothesis. The significance value has been less than 0.05, it was 0.024. it makes the case clear
that there was difference in the undertaken cases (Aravinda Rajan, 2022)
4
Both the options were available for this course of action. Sample statistics were also able to get
compared without using hypotheses method, but the key aim of the research was to provide more
reliable framework which is only possible by imparting the test. At the same time, extrapolation
of data can only be made possible if hypothesis testing has been used. These all arguments were
taken into consideration before making this choice.
The research was conducted using systematic approach so for drowning conclusion there was
need of having the same set of practise. Such as fabrication of hypotheses, setting up significance
level then making comparison with corresponding value and at the end extending final outcomes

so these has been the reasons behind giving preference to the testing over normal comparison
method.
Case study-2 Entrepreneurship Intention
1. On the basis of evaluation made with respect to the entrepreneurship intention scores, out of
134 respondents, 60 of them found to be not having taken the entrepreneurship module while the
remaining 74 have taken the module in entrepreneurship. Accordingly, the average score of these
two groups are found to be 20.917 and 22.230 respectively. On performing homogeneity test
through Levene’s test, it has been determined that the significance value comes out to be greater
than 0.05 that is 0.310 and accordingly, it can be stated that there is no significant relationship
between having taken or not the entrepreneurship module and the test score for entrepreneurship
(Emmert-Streib and Dehmer, 2019). Also, the normality test has been performed which involves
Shapiro – Wilk’s test and the results obtained are found to be higher than the standard of 0.05
that is, 0.324. Accordingly, it can be stated that null hypotheses must be accepted which means
there is no relationship between attaining or not attaining entrepreneurship module and test score
for entrepreneurship intention.
2. Here the hypotheses stating whether there is any statistical significance lies between average
test score obtained by students for entrepreneurship intention has been tested through
independent sample t-test which gives the p value as 0.009. Therefore, due to being p value
lower than the standard criteria of 0.05, it can be said that the acceptance must be for alternative
hypotheses indicating that the average test score obtained for entrepreneurship intention by those
who have attended module in entrepreneurship and those who have not are significantly
different.
3. In order to test that if there is any impact of university department over the average score
gained in entrepreneurship module, the ANOVA test has been applied. This results in
significance value of 0.001 that is, lower than 0.05 and accordingly, it can be said that there is
significant impact of university department over the test score associated with entrepreneurship
intention. This in turn would results in the acceptance of alternative hypotheses and rejection of
null hypotheses.
5. p value is the number resulting from the application of statistical test which explains the
probability of getting a specific set of observations in the event of null hypotheses found to be
true. It is useful while testing hypotheses through different statistical tests, to determine whether

the null hypotheses should be accepted or rejected (Ding, Denain and Steinhardt, 2021). P means
probability associated with the assumption of no difference or no effect of getting a result
equivalent to or greater than what actually was observed. A low value obtained for p means the
results would be replicable while a higher value of p results in situation where it becomes
necessary to reject null hypotheses.
The limitation of p value involves that it is capable of measuring the data compatibility with the
null hypothesis while it could not measure the probability of null hypothesis being correct. Also,
p value is not capable of indicating whether the model or test applied for testing the hypotheses
is good or best fit model or test.

REFERENCES
Chukhrova, N. and Johannssen, A., 2021. Fuzzy hypothesis testing: Systematic review and
bibliography. Applied Soft Computing. 106. p.107331.
Greenland, S., 2021. Analysis goals, error‐cost sensitivity, and analysis hacking: Essential
considerations in hypothesis testing and multiple comparisons. Paediatric and
Perinatal Epidemiology. 35(1). pp.8-23.
Hameed, K., Chai, D. and Rassau, A., 2020. A sample weight and adaboost cnn-based coarse to
fine classification of fruit and vegetables at a supermarket self-checkout. Applied
Sciences. 10(23). p.8667.
Rigner, A., 2019. Ai-based machine vision for retail self-checkout system. Master's Theses in
Mathematical Sciences.
Aravinda Rajan, V., 2022. Automation of Shopping Mart by Self-Checkout System using
IOT. ESP Journal of Engineering & Technology Advancements. 2(2). pp.1-5.
Ding, F., Denain, J. S. and Steinhardt, J., 2021. Grounding Representation Similarity Through
Statistical Testing. Advances in Neural Information Processing Systems, 34, pp.1556-
1568.
Emmert-Streib, F. and Dehmer, M., 2019. Understanding statistical hypothesis testing: The logic
of statistical inference. Machine Learning and Knowledge Extraction, 1(3), pp.945-962.

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