amb201 marketing & audience research file · web viewgabriella mcsweeneyquantitative...
TRANSCRIPT
Gabriella McSweeney Quantitative Project 2 N9422765
Queensland university of technology
AMB201 Marketing & Audience Research
Quantitative Report – Project 2 Topic: Predictors of Online Retail Shopping
Gabriella McSweeney – N 9422765
22nd of October 2015
Jay Kim – Tutorial 3pm-4pm Thursday’sWord Count: 1920
Table of Contents(i) Participation Reflection..................................................................................................................2
0
Gabriella McSweeney Quantitative Project 2 N9422765
(ii) Executive Summary/ abstract.....................................................................................................4
1.0 Introduction and Background.................................................................................................5
1.1 Importance of the research..................................................................................................5
1.2 Scope of the report..............................................................................................................5
1.3 Research problem/question.................................................................................................5
1.4 Aims and Objectives...........................................................................................................6
2.0 Method...................................................................................................................................7
2.1 Methodological considerations and assumptions................................................................7
2.2 Sample considerations........................................................................................................7
2.3 Data collection and framework, and analytical considerations...........................................9
3.0 Ethical considerations...........................................................................................................10
4.0 Analysis................................................................................................................................11
4.1 Cleaning and Editing........................................................................................................11
4.2 Descriptive Analysis.........................................................................................................11
4.3 T – Test Analysis..............................................................................................................12
4.4 Self-Concept.....................................................................................................................13
5.0 Discussion and Recommendations.......................................................................................18
5.1 Interpretation of the data based on the analysis you have undertaken...............................18
5.2 What this means for managers and for the next stage of the research...............................19
6.0 Limitations...........................................................................................................................20
6.1 Factors that affect the confidence that you have in your findings that impact your recommendations..........................................................................................................................20
7.0 References............................................................................................................................21
(i) Participation Reflection
Why you selected a particular project to participate in;
1
Gabriella McSweeney Quantitative Project 2 N9422765
As a part of AMB201 Quantitative Project 2, I participated in two (2) research projects on the
following topics:
- Evaluation of Media Announcements
- Consumer Ratings of Association: cities and tourism, brands and crisis, consumer
goods
I selected the above research topics as I found them the most interesting and appealing to me.
I believed that I would be able to give good insight to the researcher as I am confident and
aware of the topics.
What was involved in participating and what insights have you gained?
The initial stage of participating in these surveys was placing myself at a desk with a
computer. I read the consent form and signed the form prior to undertaking the research
questions. The first quantitative project on the evaluation of media announcements I read a
range of announcements on brands/labels and sponsoring certain events and then solved a
puzzle. After that was completed I was asked to try and remember the brands and companies
that sponsored/matched with the correct event. The puzzle was challenging as I was required
to remember which sponsors matched to each event. The second quantitative project on
consumer ratings of association was slightly similar. In the first part I had two words given to
me which I had to rate from weak, moderate or strong on how much they were associated
with each other. After completing a range of different ones on cites and tourism, brands and
crisis and consumer goods I was required to solve a puzzle. Similar to the other quantitative
project I was then required to try and remember which ones went together.
How you might use this experience to inform your own research;
After participating in this experience it has enable me to look at how researchers obtain data
from surveys. I believe that the survey projects were done creatively and effectively. I found
that the researcher used the puzzles as a distraction so the researcher would obtain the data
that stood out the most for the participant.
Whether you feel it is valuable for researchers to also take part in research as a participant.
After taking part in the whole experience I strongly believe it is essential for researchers to
take part in the research as a participant. Similar to the qualitative projects, I believe the
researchers will have a better understanding of where the participants are coming from when
they undergo the survey process and experience some of the pressure the participants may feel
towards answering certain questions. Similarly researchers will provide their own feedback at
the end and will relate more to the responses as they answered the same questions in the
2
Gabriella McSweeney Quantitative Project 2 N9422765
survey. Researchers can also recognise and make improvements to the questions in future
research to avoid bias.
3
Gabriella McSweeney Quantitative Project 2 N9422765
(ii) Executive Summary / Abstract
Descriptive Analysis Design is aimed to describe the characteristics of a target population and
is able to provide conclusive information. The aim of this Quantitative Research report is to
focus on the analysis of determinates that either influence or do not influence Australian
consumer’s attitudes towards online retail shopping.
Researchers are able to draw conclusions about the target population based on the sample. In
this report the target population is English speaking women from an age cohort of 18-40 years
and 41+ years and who regularly use the internet and uses quota, non-probability sampling.
The research method for collecting data was through surveys which collected large amounts
of data using a question and answer format. Due to the nature of the sampling techniques used
it is known that errors can arise. It is recognized that non response bias may be present so
researchers must ensure that the sample is representative of the target population. Though
sampling can be seen as an efficient form of data collection inaccuracy in survey data can
occur.
Due to the descriptive nature of this report the data needs to be accurate and considered in all
aspects of this report. In addition, ethics has to be considered in relation to confidentiality and
analysis of the data collection process.
It was revealed that convenience seeking, variety seeking and risk aversion were main
constructs that influenced consumers attitudes towards online retail shopping. Three (3) out of
the four P’s - place, promotion, and price can be adopted by markets to help fulfil consumers’
needs. It is recommended from this descriptive study that it may be of benefit for researchers
to conduct casual research to look and explain the cause and effect relationships between the
variables.
Non-probability sampling and social desirability bias are the limitations of this report.
4
Gabriella McSweeney Quantitative Project 2 N9422765
1.0 Introduction and Background
1.1 Importance of the Research
Descriptive analysis provides in-depth description of a target population in order to
draw meaningful conclusions from the research. This report is an extension to the
previously conducted exploratory and qualitative report, which explored the
characteristics of the target population rather than describing the characteristics of the
target population (Hair, 2014 , p. 12). From a theoretical point of view, researchers
must identify the concepts relevant to the research problem to obtain high quality data.
The goal of the construct development process is to precisely identify and define what
is to be measured (Hair, 2014 , p. 279). Literature reviews are also frequently used by
marketing researchers. Literature reviews are a comprehensive examination of
available information related to a topic of interest (Hair, 2014 , p. 59). From a
practical point of view marketing research is important as it is able to provide
background information for the current study, helps to inform researchers or managers
of consumer behaviour such as wants and needs that motivate them to buy, and helps
to advise the way marketers should engage with their consumers now and in the
future.
1.2 Scope of the Report
The scope of this report includes a descriptive analysis of survey data collected. This
report is based on self-reported behaviour and it aims to identify the determinants of
Australia consumer’s attitudes towards online retail shopping. This analysis includes
aspects of t-testing, correlation and regression all of which are comparative to
developed constructs. Surveys have been used to quantitatively examine the drivers of
online retail shopping behaviour. For anyone engaged in online retail, and for
marketers in general, it is important to know who these shoppers are, what motivates
them to buy, and how they might best be reached.
1.3 Research Problem/Question
Australians have embraced online retail shopping, highlighting the tangible benefits of
the digital economy (ACMA, 2011). Consequently, researchers want to understand
what the determinants of Australian Consumers’ attitudes towards online retail
shopping.
5
Gabriella McSweeney Quantitative Project 2 N9422765
1.4 Aims and Objectives
The aim of this report is to quantitatively explore determinates of the Australian
Consumers’ attitudes towards online retail shopping. To achieve this aim the
following objectives are key components of the research question:
i. To examine how self-concept dimensions relate to online retail shopping
attitudes
ii. To determine the impact of individual characteristics on online retail shopping
attitudes
iii. To evaluate how social desirability might influence the results of the research
6
Gabriella McSweeney Quantitative Project 2 N9422765
2.0 Method
2.1 Methodological Considerations and Assumptions
Descriptive research is used to describe the characteristics of given data in relation to a
research objective. Descriptive research does not address any ‘why’ questions
associated with a given research problem like exploratory research does, however it
does provide answers to the ‘how, what, where, when and who’ questions (Hair,
2014 , p. 12). Casual research is used to identify “cause and effect” relationships
(Hair, 2014 ). Due to this report being a quantitative research method it allows the
researcher to infer certain characteristics of a population, given the sample (Hair, 2014
, p. 12). This research was conducted through surveys using cross –sectional research
with data collected at a single point in time (Hair, 2014 ). Assumptions can be made in
using survey’s such as, the sample size is sufficient to reflect the target population and
participant’s insights are accurately recorded to gain greater insight. Therefore it is a
descriptive methodology for gathering quantitative data from a large group of people.
2.2 Sample Considerations
We identified whether a sample or census was needed to be considered. Due to the
nature of this report, a sample was conducted as it is more practical regarding cost,
time and the research design. By using a sample we are able to have generalisations
across the whole population. The sample of this data aims to infer attitudes of online
retail shopping about a population. The following stages of sampling model have been
used as the framework in sampling considerations from Marketing Research, by
Joseph Hair (Hair, 2014 ).
The Target population for this report includes English-speaking adults, above the age
of 18 who regularly use the internet. Enabling to quantitatively explore determinates
of the Australian Consumers’ attitudes towards online retail shopping
There is no sample frame.
7
1. Define the Target Population
2. Select a Sample Frame
Gabriella McSweeney Quantitative Project 2 N9422765
Non-Probability Sampling was considered and some elements of the population have
zero probability of being selected for this study.
Quota Sampling was considered, which forces researchers recruit certain
demographics. It enables us to have an equal number of males and females and age
group. In this report for example, respondents must be above 18years old, internet
users and English speaking. Two groups were formed to conduct in the survey being
between 18-40 years of age and the other group being 41 + years of age.
After cleaning, coding and response checks of the data was conducted the sample size
was equal to 659. As the sample size is relevantly large it is more representative of the
population making it an appropriate sample size (Unite for Sight , 2009-20015).
Units used to determine sample size include men aged 18-40 years, men 41+ years,
women aged 18-40 years and women 41+ years.
Market researcher goes out to collect data and framework.
8
3. Probability or Non-Probability Sampling
4. Plan procedure for selecting sampling units
5. Determine Sample Size
6. Select Actual Sampling Units
7. Conduct Fieldwork
Gabriella McSweeney Quantitative Project 2 N9422765
2.3 Data Collection and Framework and Analytical Considerations
For this report data was collected through surveys, which seek to gather large
quantities of data using question-and-answer format (Hair, 2014 , p. 171). As this
study is using a larger sample size using surveys it is an appropriate research method.
The survey uses free response questions, scale item questions, simple dichotomy,
frequency determination questions and checklist questions. Participants collected two
surveys based on their family names being names beginning with A-L conducted 2
surveys from each ago cohort: Men (18-40 years) Men (41+years) and names
beginning M-Z conducted 2 surveys from each age cohort: Women (1-40 years)
Women (41+years). Surveys can be communicated through face to face conversation,
over the phone and internet (Hair, 2014 , p. 180). For this report the surveys were
communicated through email by sending the participants the surveys for them to
complete and send back for data collection.
Data was then cleaned and coded, and the results were obtained. SPSS data analysis
software was used to reverse response to negatively phrases survey items. Constructs,
concepts and operationalization were used. Constructs being concepts or generalised
ideas that stand for something of meaning regarding the research topic for marketing
research (Hair, 2014 , p. 279). Constructs were calculated to determine response
averages across the relevant items. Operationalization gives meaning to a concept by
specifying the activities or operations necessary to measure it (Hair, 2014 , p. 286).
Frequency tables and crosstabulations were formulated to initially describe the dataset.
T-test analysis, correlation and multiple regression were then used to more explicitly
explore the attitudes towards online retail shopping.
Non-response bias is considered in this report and may be inclined to arise due to the
nature of the sampling techniques used. Though it has been said that using a sample
can be a sufficient form of collecting data it cannot always be the most accurate and
relevant form of information. Non – response error is a systematic bias that occurs
when the final sample differs from the planned sample (Hair, 2014 , p. 176). This is
likely to occur when a sufficient number of the prospective respondents in the sample
cannot be reached for participation (Hair, 2014 , p. 176). In this report non-response
bias has to be considered when analysing and discussing the data and for
recommendations.
9
Gabriella McSweeney Quantitative Project 2 N9422765
3.0 Ethical Considerations
Ethical and unethical behaviours manifest in the research process (Hair, 2014 ). The
Researcher must consider the ethical issues directly and indirectly that affect the development
and evaluation of the research report (Hair, 2014 ). Maintaining an ethical approach during
the research process is extremely important because consumers are more likely to contribute
during the research (Angelo, 2012). Marketing research relies on the systematic gathering and
interpretation of information from individuals, organisations and the general public (AMSRS,
2015). Consumers of research rely on research being carried out honestly, objectively and in a
manner that protects participants ‘rights’ (The Queensland University of Technology, 2015).
It is critical for the researcher and the participant to establish a strong relationship and it is
through this relationship that all data are collected and data validity is strengthened (Burkard,
2009). In addition, respect between the research and the person being surveyed will help
ensure that there are accurate and honest responses to the questions.
Ethics refers to the accepted rules and standards that govern the conduct of members of a
given group or profession (The Queensland University of Technology, 2015). The
Queensland University of Technology has clear principles for the responsible conduct of
research that all staff researchers and research students have to comply. The research policy
states that ‘Research at QUT is undertaken in an ethical and accountable environment, based
on shared commitment by the University and its researchers to maintain a strong culture of
integrity and fair conduct.’ (The Queensland University of Technology , 2015) . The research
conducted for this project does meet the above ethical policy as the researcher ensured that the
person being surveyed reviewed and read the interview consent form and signed it before
proceeding.
10
Gabriella McSweeney Quantitative Project 2 N9422765
4.0 Analysis
4.1 Cleaning and Editing
Quantitative data analysis requires that the data obtained is subject to data cleaning
and editing in order to remove invalid and inaccurate data. Data cleaning and editing
allows researchers to properly analyse data. In this analysis, data was cleaned but
issues identified with items where respondents could freely enter data and corrections
were then made. Doing this by deleting respondents with uninterpretable responses
and non-existent postcode, converting birth year to age in years and estimating
approximations. For example ‘21 years old’ can be cleaned and edit to ‘21’.
Frequencies were also run to check vales were all in range, for example all ages within
the range of no one less than 18 years. The data was then reverse coded and following
the constructs were then calculated.
4.2 Descriptive Analysis Descriptive data is very important because if we simply presented our raw data it
would be hard to visualize what it is showing; therefor it allows us to make
conclusions beyond data we have analysed to reach conclusions (aerd Statistics ,
2013). Table 1 indicates means and standard deviations for each developed construct.
The overall sample size after the cleaning of the data was 659. The lowest mean score
of 1.4980 and lowest standard deviation score of 0.21652 was social desirability. The
Constructs of risk aversion, variety seeking, convenience seeking and price
consciousness indicated fairly low standard of deviations indicating that the mean is a
good representation of the data. ATTBI as a mean of 4.9727 with a standard
deviation of 1.49702 which is the highest standard deviation in this construct set.
Therefore, the mean is not exactly a good representation of the whole data set.
11
Gabriella McSweeney Quantitative Project 2 N9422765
Table 1: Descriptive Statistics Constructs Mean Std.Deviation
ATTA 4.4256 1.38845
ATTC 5.0847 1.25722
ATTBI 4.9727 1.49702
Risk Aversion 4.6171 0.94226
Impulsiveness 3.7075 1.15526
Variety Seeking 4.4917 0.78855
Convenience seeking 4.7657 0.79547
Price Consciousness 4.9522 0.99876
Social Desirability 1.4980 0.21652
4.3 T – Test Analysis
A T – test analysis assists to understand and evaluate how likely it is that any apparent
difference has occurred between the two given variables relative to the research
problem. The significance level represents the probability that any difference that has
been observed is due to chance. The significance level was tested at 0.05%
Significance.
4.3.1 Significant Difference
After looking at the results of analysis based on which method of online
communication do you more frequently use, the mean for email
communication was 4.540, while the mean for online chat was 5.4118.
Assuming equal variances, the T-test displayed that the difference between the
means was significantly different with the T-test score being -7.806 with a
significance of 0.000. This reflects that there is a difference between the mean
of email and online chat. Therefore it shows that the attitude towards online
retail shopping does differ between these two forms of communication.
Table 2: Group Statistics - Email and Online Chat
12
Which method of online communication do you more frequently use?
N Mean Std. Deviation Std. Error Mean
Email 332 4.5402 1.52347 .08361Online Chat 327 5.4118 1.33523 .07384
Gabriella McSweeney Quantitative Project 2 N9422765
Table 3: T-Test - Email and Online Chat T – Test of Equality of Means
ATTBI
Equal variance assumed
t df Sig. (2-tailed)
-7.806 657 .000
4.3.2 No significant Difference
After looking at the results of analysis based on gender, male or female, the
mean of male was 4.9005, while the mean of female was 5.0429. Assuming
equal variances, a t-test displayed that the difference between the means was
not significantly different, with the t-test score being -1.221 and a significance
of 0.222. This reflects that there is no significant difference between the mean
of gender, male and female. Therefore it shows that the attitude toward online
retail shopping does not differ between male and female.
Table 4: Group Statistics – Gender, Male or Female
Table 5: T-test – Gender, Male or Female
T – Test of Equality of Means
ATTBI
Equal variance assumed
T df Sig. (2-tailed)
-1.221 657 .222
4.4 Self-Concept Semantic differential scales were used to measure a range of self – concept
dimensions. Rather than averaging across items, it was conducted by examining how
the various self – concept dimensions correlate with attitudes towards online retail
shopping. The significance level was tested at 0.05% significance.
4.4.1 Significant Positive Correlation
13
What is your Gender N Mean Std. Deviation Std. Error Mean
Male 325 4.9005 1.49302 .08282Female 334 5.0429 1.49980 .08207
Gabriella McSweeney Quantitative Project 2 N9422765
The data chosen for this example includes the dimension of conventional to
unconventional. Results showed a significant correlation between conventional
to unconventional and attitudes towards online retail shopping, with a
correlation of 0.150 and a significance of 0.000. This significant positive
correlation indicates that as unconventional towards online retail shopping
increases so does the overall attitude.
Table 6: Significant Positive Correlation
Self-Concept Dimension ATTBI
Conventional|||
UnconventionalPerson Correlation 0.150
Sig (2-tailed) 0.000
N 659
4.4.2 Significant Negative Correlation
A significant negative correlation includes a sematic dimension of innovative
to routine and attitudes towards online shopping, with a correlation of -0.238
and a significance level of 0.000. This significant negative correlation indicates
that as routine grows attitudes towards online shopping decreases.
Table 7: Significant Negative Correlation
Self-Concept Dimension ATTBI
Innovative|||Routine Person Correlation -0.238
Sig (2-tailed) 0.000
N 659
4.4.3 Non-Significant Correlation
The dimension of uncomfortable to comfortable and attitudes towards online
shopping represent a non-significant correlation, with a correlation of 0.022
and a significance level of 0.565. As this is an insignificant correlation it
indicates that there is no relationship to indicate that as someone becomes
more comfortable so do attitudes towards online shopping.
14
Gabriella McSweeney Quantitative Project 2 N9422765
Table 8: Non-Significant Correlation
Self-Concept Dimension ATTBI
Uncomfortable|||Comfortable Person Correlation 0.022
Sig (2-tailed) 0.565
N 659
4.5 Multiple Regression
Multiple regression tests determine how a set of independent variables impact on
dependent variable. All variables were tested at 0.05 significance.
4.5.1 All Respondents
Multiple regression was used to analysis the data. Based on the results this
showed an R value of 0.623 and an adjusted R squared value of 0.383. This
indicates that there is a 38.3% of variation of attitudes towards online retail
shopping can be explained by the predictors of the model. The two more
important predictors in explaining variation in attitudes towards online retail
shopping are variety seeking with a coefficient 0.290 and a significance level
of 0.000 and convenience seeking with a coefficient of 0.285 and a
significance level of 0.000. Figure 1 below displays the construct model for the
analysis of variety seeking and convenience seeking indicating a greater
impact on the construct of this model. It is noticed that impulsiveness showed
no level of significance and impact towards attitudes of online retail shopping,
with a coefficient of -0.005 and a significance level of 0.879. Risk Aversion
and Impulsiveness are in inverse relationships. For example, when Risk
Aversion increases attitudes towards online retail shopping decreases.
Table 9: Model Summary
Model R R Square Adjusted R
Square
Std. Error of
Estimate
1 0.623 0.388 0.383 1.17564
15
Gabriella McSweeney Quantitative Project 2 N9422765
Table 10: ANOVA Analysis of Variance
Model Sum of
Squares
df Mean
Square
F Sig
1 Regression 572.090 5 114.418 82.784 0.000
Figure 1: Model Predictors of Online Retail Shopping Attitudes
B=-.581
B=ns
B=.551
B= .537
B=ns
16
Individual Characteristics Risk Aversion
Impulsiveness
Variety Seeking
Convenience Seeking
Price Consciousness
Attitudes towards online retail shopping
Gabriella McSweeney Quantitative Project 2 N9422765
4.6 Social Desirability Bias
An analysis of social desirability scores within our sample has been undertaken. Social
desirability can be spilt into high and low desirability to differ people’s responses. The
social desirability was measured by answering ten (10) yes or no questions to be able
to engage how they present themselves more or less favourably then what is actually
the case. Figure 2 below of the histogram represents a visual inspection of the data set.
Most people were getting the social desirability score around the average mark of 1.50
indicting that most people have some social desirability and want to positively present
themselves. It is important to be more cautious with interpreting data when social
desirability is present as over interpreting the data can cause the data not to be
accurate.
Figure 2: Social Desirability
17
Gabriella McSweeney Quantitative Project 2 N9422765
5.0 Discussion and Recommendations
5.1 Interpretation of the data based on the analysis you have undertaken
i. To examine how self-concept dimensions relate to online retail shopping attitudes
After analysis of the data, self-concept dimensions displayed characteristics of
attitudes towards online retail shopping. It has been understood that as a person’s
level of unconventional grows as does their attitudes towards online retail
shopping positively increase. It is notice that online retail shoppers are more
unusual consumers rather than conservative consumers. There is no relationship to
indicate that as someone becomes more comfortable so do their attitude towards
online shopping.
ii. To determine the impact of individual characteristics on online retail shopping
attitudes
In the previous exploratory report it was discovered that price, convenience and
being a time poor society were determinates of online retail shopping. From the
descriptive analysis it has be understood that convenience seeking and variety
seeking are the main characteristics that influence attitudes towards online retail
shopping. In summary, convenience seeking, variety seeking and risk aversion are
the individual characteristics that have the greatest impact on attitudes towards
online retail shopping.
iii. To evaluate how social desirability might influence the results of the research
Social desirability bias is when a person acts or changes their personal view to suit
a socially acceptable response (DeMaio). For this study, social desirability bias
may affect the accuracy of the sample data. It is important to be more cautions
when looking at social desirability as then the data is considered more accurate and
reliable.
18
Gabriella McSweeney Quantitative Project 2 N9422765
5.2 What this means for managers and for the next stage of the research
Managers are going to have to adapt to the ongoing changes in the market and look at
trends in order to survive. Managers will need to re-assess their marketing plans by
looking at the four P’s of marketing. Product, Price, Place and Promotion need to be
reviewed to ensure that they satisfy consumer’s needs with variety, convenience and
risk aversion. Developing websites that allow customers to conveniently browse and
purchase items will fulfil consumers’ needs of convenience seeking. The development
of return policies to enable consumers to return goods for any reason will greatly
improve consumers online purchasing as it will reduce the risks associated with the
transaction. In addition, consumers will be greatly influenced by the website having a
large variety and range of products available for purchase. Overall, businesses must
adopt elements of the marketing mix so it can enhance convenience and variety so that
it can capture the attention of consumers.
It may be useful for managers and researchers to conduct a causal study. A casual
research design seeks to understand the cause – and – effect relationships among two
or more decision variables (Hair, 2014 , p. 12). In addition, understanding the cause-
effect relationships among market performance allows the decision-maker to make if-
then statements about the variables (Hair, 2014 , p. 12).
19
Gabriella McSweeney Quantitative Project 2 N9422765
6.0 Limitations
6.1 Factors that affect the confidence that you have in your findings that impact
your recommendations
The major limitations of this research that impact confidence in the recommendations
provided are non-probability sampling and social desirability bias. Due to having no sample
frame, non – probability sampling was used. Non-probability sampling can be a limitation
that affects the sample of the data that is provided. In non-probability sampling it is known
that participants are not randomly selected to be a part of this survey. Therefore, when making
recommendations it is not entirely certain that information is reflected of the population.
However non-probability sampling is fast to do and doesn’t require much skill. Social bias
could affect some of the respondent’s answers on surveys which then cause recommendations
to not be accurate. It is important to apply reliability and validity to your research and data
collection.
It is important when implementing surveys to ensure accuracy, researchers must resolve a
variety of issues associated with construct development, scaling and questionnaire design
(Hair, 2014 , p. 173). A limitation of this being that issues can produce many kinds of errors
in survey findings. As the possibility of systemic error increases, so does the likelihood of
collecting irrelevant or inaccurate data (Hair, 2014 , p. 173). Non- response bias may also be a
limitation due to the nature of the sampling techniques used.
20
Gabriella McSweeney Quantitative Project 2 N9422765
7.0 References
Abeyasekera, S. (n.d.). Quantitative Analysis Approaches to Qualitative data - why, when and how . Retrieved from http://www.reading.ac.uk/ssc/resources/Docs/Quantitative_analysis_approaches_to_qualitative_data.pdf
ACMA. (2011). Australian Government . Retrieved September 22, 2015, from Communications 2010-2011 Report 1 - E-comerce marketplace in Australia: Online shopping : http://www.acma.gov.au/webwr/_assets/main/lib410148/CR_comp_report1-E-commerce_Marketplace_in_Australia.pdf
aerd Statistics . (2013). Descriptive and Inferential Statistics . Retrieved from aerd Statistics : https://statistics.laerd.com/statistical-guides/descriptive-inferential-statistics-faqs.php
AMSRS. (2015, May). Code of professional behaviour . Retrieved September 22 , 2015, from Australian Market & Social Research History : http://www.amsrs.com.au/documents/item/194
Angelo. (2012, June 8). Consideration on ethics in marketing research. Retrieved September 22, 2015, from Gulp: http://www.busandman.com/?p=213
DeMaio, T. J. (n.d.). Social Desirability and Survey Measurement: A Review . Retrieved from Social Desirability and Survey Measurement: A Review : https://books.google.com.au/books?hl=en&lr=&id=cQi5BgAAQBAJ&oi=fnd&pg=PA257&dq=social+desirability+definition&ots=HTzIf7EPkH&sig=pFDU__jvr3ePMI31jX1AlULdTeA#v=onepage&q=social%20desirability%20definition&f=false
Dictionary . (2015). Ethics . Retrieved September 22, 2015, from Dictionary: http://dictionary.reference.com/browse/ethics
Explorable. (2009, November 3). Quantitative and Qualitative Research - Objective or Subjective . Retrieved from Explorable: https://explorable.com/quantitative-and-qualitative-research
Hair, J. (2014 ). Marketing Research (4th ed) . North Ryde NSW, Australia: McGraw-Hill Education .
Purely Branded. (n.d.). The Four Ps of Marketing . Retrieved from News and insights - Purely Branded : http://www.purelybranded.com/insights/the-four-ps-of-marketing/
The Queensland University of Technology . (2015, July 23). D/2.6 QUT Code of Conduct for Research . Retrieved August 19, 2015, from Queensland University of Technology - Manual of Policies and Procedures : http://www.mopp.qut.edu.au/D/D_02_06.jsp
Unite for Sight . (2009-20015). The importance of Quality Sample Size . Retrieved from Unite for Sight : http://www.uniteforsight.org/global-health-university/importance-of-quality-sample-size
21
Gabriella McSweeney Quantitative Project 2 N9422765
22