Cheat Sheat
define decision problem *specify research question
*establish research objective *benefits of expected
information = report. Types of data: primary, secondary
(internal & external), customer knowledge. QUALITATIVE
RESEARCH = primary exploratory research, subjective in
nature. Advantages = cheaper, no better way to
understand in-depth motivations & feelings, can improve
efficiency of quantitative research. Limitations = many
success and failures based on small differences, not
necessarily representative of population of interest,
dominant individual can skew results. QUANTITATIVE
RESEARCH = used to quantify the problem by way of
numerical data/data that can be transformed into useable
statistics.
Basic (pure) research- attempts to expand the limits of
knowledge Applied Research- conducted when decision
must be made about a specific real-life problem
Exploratory research techniques- pilot studies, focus
group, secondary data (Qualitative)
Descriptive research- survey/questionnaire (Quantitative)
Causal Research- cause and effect among variables – test
marketing Relationships – Independent variable: stands
alone and doesn’t change by other variables you are trying
to measure (Persons age no other factor
EXPLORATORY RESEARCH: Ambiguous problem
– Objectives focus on ‘exploring’ and ‘having a
closer look’, Gaining background information, Defining
terms, Initial stage of research process, Not intended to
provide conclusive evidence, Purpose: to narrow the
scope of the research topics
– Can employ techniques from:
– Secondary data analysis o Pilot studies
– Case studies
– Focus groups
DESCRIPTIVE RESEARCH: Partially defined problem
Objectives focus on describing and measuring marketing
phenomena at a particular point in time
Already know what it is to be measured- just don’t know
how it is going to be measured
Purpose: to describe characteristics of a population (who,
what, when, where, how)
Accuracy is important
Surveys most common method (in person, telephone,
internet)
CAUSAL RESEARCH: Sharply defined problem such as
eating can change this) Dependent variable: depends on
other factors and is liable to change
Scale
Nominal: Operation – Counting I Descriptive Stats:
Frequency, Percentage, Mode
Ordinal: Rank ordering, Median, Range, Percentile ranking
Interval: Order and relative magnitude, Mean Standard
deviation, Variance
Ratio: Operations on actual quantities, geometric mean,
coefficient of variation
Traditional Tests
– Adv: Conducted in actual distribution channels. Can
determine both customer acceptance and traded
support
– Disadv: Cost, time and exposure to competition
Controlled Test Markets
– Adv: Distribution is assured, Cost are lower, Competitive
monitoring is difficult
– Disadv: Limited number of markets, trade support is
unknown
Stimulated test markets
– Adv: Cost and time saving,predict trial and purchase
cycle
– Disadv: isolation from real world, Broad based customer
reaction is difficult to measure
Experimental Design
A group of subjects is administered a treatment and then
measured (or observed). No attempt is made to randomly
assign subjects to the groups, nor does the design provide for
any additional groups as comparisons. GP – T – O
The one-shot design may be useful as an inexpensive
measure of a new treatment of the group in question.
One-group, Pre-post
One group is given a pre-treatment measurement or
observation, the experimental treatment, and a post-treatment
measurement or observation. The post-treatment measures
are compared with their pre-treatment measures.
Static group
Two intact groups are used, but only one of them is given the
experimental treatment. At the end of the treatment, both
groups are observed or measured to see if there is a
difference between them as a result of the treatment.
GP–T–O
GP —– O
Whether the groups were comparable or not is crucial in
determining the extent of information yielded by this design
Post test-only control group
Similar to static group but attempt to insure similarity of the
groups before treatment. The design works toward a
guarantee of comparability between groups assigning subjects
to groups at random.
R–GP–T–O
R–GP——O
Pretest-Post test Control Group
Adds a pre-test to the previous design as a check on the
degree of comparability of the control and experimental groups
before the treatment is given.
R–GP–O–T–O
R–GP–O——O
This yields information on pre-treatment behaviour and a
comparison of post-treatment behaviour between groups.
Avoids most threats to internal validity. Groups are comparable
because they are randomised.
Solomon Four Group
Attempts to control for the possible “sensitising” effect of the
pre-test or measurement by adding two groups who have not
been a part of the pre-test or pre-measurement process. R–
GP–T–O
R–GP–O–––O
R–GP–––T–O
R–GP–––––O
Frequently used in behaviour, educational and medical studies
where the testing process allows the subject to “learn”
Factorial design
Assign variations of the treatment. E.g. we may wish to try
kinds of treatments varied in two ways (called a 2×2 factorial
design) Some factorial designs include both assignment of
subjects (blocking) and several types of experimental
treatment in the same experiment.
R–GP–T––O
A1 B1
R–GP–T––O
A1 B2
R–GP–T––O
A2 B1
R–GP–T––O
A2 B2
Time series Design
This design, or variations of it, is used to assess the effects of
a treatment with the same group or the same individual over a
period of me. A measure, or observation is made more than
once to assess the effects of the treatment.
GP–T–O–T–O–T–O or GP–O–O–O–T–O–O–O
There is no randomisation oftest units to treatments. The
timing of treatment presentation, as well as which test units
are exposed to the treatment, may not be within the
researcher’s control. e.g. ad spending on sales Exampleplain
packaging law of cigarette sales
Simple Random Sampling (SRS)
– Researchers use a table of random numbers, random
number generator or some random selection procedure
that ensures that each sampling unit make the target
population
Systematic Random Sampling
– More efficient than SRS. If we think target population has a
non-normal ( or skewed) distribution for one or more of its
distinguishing characteristics (e.g. age, income, product
ownership), researchers must identify sub-populations,
referred to as strata. After the strata are segmented a
simple random sample is drawn for each stratum.
Stratified Random Sampling
– When the defined target population is believed to have a
non-normal (skewed) distribution for one or more of its
distinguishing characteristics (age, sex, income, etc),
researchers must identify sub-populations referred to as
‘strata’
After ‘strata’ are segmented, a simple random sample is
drawn for each stratum
Cluster Sampling
Requires the defined target population to be segmented into
geographic areas, each of which are considered to be very
similar to the others
Researchers randomly select a few areas, then conduct a
census of what the elements in each are
NON-PROBABILITY SAMPLING METHODS:
Convenience sampling
Samples drawn at the convenience of the researcher/
interviewer, often as the study is being conducted
Has potential for a lot of bias, but does it really make that
much of a difference?
Judgment sampling
Participants selected according to the researcher’s or some
other experienced individual’s belief that they will meet the
requirements of the study
Whole population is not of interest Looking for a specific
target market
Quota sampling
– Selection of prospective participants according to the prespecified
quotas regarding demographic characteristics
o Demographics (age, race, sex, income) o Specific attitudes
(satisfied/dissatisfied, liking/disliking, great/marginal/no
quality) o Specific behaviours (regular/occasional/rare, user/
non-user, heavy/light)
– Underlying purpose: to provide assurance that pre-specified
subgroups of the defined target population are represented
on pertinent sampling factors that are determined by the
researcher or client, Cross-section
Snowball sampling
– Identifying and qualifying a set of initial
prospective respondents who can help the researcher identify
additional people to be included in the study
– After interviewing one person, the interviewer would solicit
that person’s help to identify other people with similar
characteristics, opinions or feelings
MEASUREMENT:
Goal: to obtain high-quality data
Construct development
o Construct abstractness o Construct dimensionality o
Construct development
– Precisely identify and define what is to be measured
– Hypothetical variable comprised of responses or behaviours
that are thought to be related
Construct abstractness- concrete vs subjective properties; the
more subjective, the more abstract Construct dimensionalityidentifiable
and measurable components that constitute the
domain of observables
Construct validity- process of establishing that the construct is
valid, by testing for content, convergent, discriminant and
nomological validity
Construct operationalisation- process of explaining a
construct’s meaning in measurement terms by specifying the
activities to measure it
CONSTRUCT
Concept- generalised idea
Conceptual- verbal explanation of the meaning of a concept (what
it is and what it is not)
Operational- gives meaning to a concept by specifying the
activities or operations necessary to measure it
SCALE RELIABILITY & VALIDITY
3 criteria for good measurement:
Reliability – degree to which measures are free from random error
Split-half method – to determine constancy by checking one half of
a set of results against the
Errors:
• Random sampling error: e.g. caused by choosing only 50
respondents who enrolled into MKTG202 to represent the
population of all the MQ students.
Unavoidable but can be estimated (calculating confidence
intervals) or reduced (increasing sample size).
• Systematic error (non-sampling error) Systematic error results
from some imperfect aspect of the research design or from a
mistake in the execution of the research. Can be managed
(research execution)
• Sample Bias (respondent error) Persistent tendency to deviate
in one direction from the true value of the population parameter.
• Systematic error: respondent error sample bias/error resulting
from some respondent action or inaction.
• Non-response error: The statistical differences between a
survey that includes only those who responded and a perfect
survey that would also include those who failed to respond. –
caused by those who are not involved in the research, not
knowing what is unknown. Non-respondent: a person who is not
contacted or who refuses to cooperate in the research.
No contact: a person who cannot be reached on the 1st or 2nd
contact e.g. target population members not online. Refusalperson
unwilling to participate in research. Self-selection biaspeople
who feel strongly about a subject are more likely to
respond to survey question than people who feel indifferent
about it e.g. those volunteers to do the research.
• Response bias: respondents tend to answer questions with a
certain bias that consciously or unconsciously misrepresents the
truth. Deliberate falsification: occasionally people deliberately
give false answers to appear intelligent, conceal personal
information etc. Common when interviewing children and
politicians. Unconscious misrepresentations: response bias
arising from question format or content, even when respondent
is trying to be truthful. Acquiescence bias: some individuals tend
to agree with all questions e.g. caused by an obedient
respondent who chooses “yes”/” agree” to all questions
Extremity bias- some individuals tend to use extremes when
responding to questions. A respondent ticks the lowest or
highest marks for all questions, difference between eastern and
western.
• Auspices bias- respondents are influenced by the organisation
conducting the study e.g. questions about general shopping
experiences asked within a Woolworths. Social desirability biasrespondents’
desire, either conscious or unconscious to gain
prestige or appear in a different social role e.g. questions related
personal or moral behaviour.
• Surveys may be classified according to several criteria. A
structured question is a question that imposes a limit on the
number of allowable responses, where as an unstructured
question is a question that does not restrict the respondents’
answers. They are open-ended and allows the respondent
considerable freedom in answering. The research must also
decide whether to use undisguised questions, which are
straightforward and assumes that the respondent is willing to
answer, or disguised questions, which are indirect and assumes
that the purpose of the study must be hidden from the
respondent. However, these classifications have two limitations.
• First the degree of structure and the degree of disguise vary;
they are not clear-cut categories. Second, most surveys are
hybrids, asking both structured and unstructured questions.