Chapter Nine:

Conducting Marketing Experiments

1. Know the basic characteristics of research experiments:

1.1 Subjects: sampling units for an experiment, usually human participants in

research who are subjected to some experimental manipulation. Researchers refer
to participants in experimental research as subjects – instead of respondents. This is
because the research subjects research participants to some experimental
treatment.

1.2 Experimental conditions: one of the possible levels of an experimental variable

manipulation. Perhaps the characteristic that most differentiates experimental
research from survey research is the manner in which independent variables are
created rather than simply measured. For example colour and lighting, changing the
brightness of the light or making a store predominantly green or red – alter the
experimental conditions the subject is exposed to.

Blocking variables: categorical variables include in the statistical analysis of

experimental data as a way of statistically controlling or accounting for variance due
to that variable. For example, the subjects gender or age.

Covariate: a continuous variable included in the statistical analysis as a way of

statistically controlling for variance due to that variable. Covariate is treated like a
regression variable.

Measured independent variables are called blocking and covariate variables in

experiments.

1.3 Effects: are the characteristics of experiments that allow hypothesis to be tested.
Effects can be classified into main effects and interaction effects. Main effects – the
experimental difference in means between the different levels of any single
experimental variable. Interaction effect – differences in a dependent variable due to
a specific combination of independent variables.
 2. Basic issues of experimental design:

Experimental design involve these FOUR design elements:

2.1 Manipulation of the independent variable:

The thing that makes independent variables special in experimentation is that the
researcher can create its values. This is how the researcher manipulates, and
therefore controls independent variables. For example, with colour – the researcher
can choose either red or green as the colour of the store.

Experimental independent variables represent hypothesized causal influences.

Therefore, experiments are appropriate in casual designs.

An experimental treatment is the term referring to the way an experimental variable

is manipulated. For example, assigning different subjects randomly to evaluate
eithera green or red store environment.

In the simplest experiment, the researcher manipulates an independent variable over

two treatment levels resulting in two groups, an experimental group (A group of
subjects to whom an experimental treatment is administered) and control groups (a
group of subjects to whom no experimental treatment is administered which serves
as a baseline for comparison).

2.2 Selection and measurement of the dependent variable:

Selecting dependent variables are crucial in experimental design. Unless the

dependent variables are relevant and truly represent an outcome of interest, the
experiment will not be useful.

Choosing the correct dependent variable is part of the problem definition process.
The experimenter’s choice of dependent variable determines what type of answer a
researcher can provide to assist managers in decision making.

2.3 Selection and assignment of experimental subjects

Test units are the subjects or entities whose responses to the experimental
treatment are measured. Individual consumers, employees, organisational units can
be test units

Sample selection and random sampling errors: errors may occur in experimentation.
Systematic or non-systematic error may occur if the sampling units in an
experimental cell are somehow different than the units in another cell, and this
difference affects the dependent variable.

Randomization: the random assignment of subject and treatment to groups, if it is

one device for equally distributing the effects of extraneous variables to all conditions

Matching subjects on the basis of pertinent background information is another

technique for controlling systematic error. Matching involves assigning subjects in a
way that a particular characteristic is the same in each group. For example, equal
number of men and woman in each group.

Repeated measures: experiments in which an individual subject is exposed to more

than one level of an experimental treatment.

2.4 Control over extraneous variables

The fourth decision concerns control over extraneous variables that may influence
the dependent variables.

Experimental confounds: an experimental confound means that there is an

alternative explanation beyond the experimental variables for any observed
differences in the dependent variables.

Identifying extraneous variables: because extraneous variables van produce

confounded results, researchers must make every attempt to identify them before
the experiment.

3. Know tools for maximising the validity of experiments with an emphasis

on minimising demand characteristics

Most experiments involve some directed task performed by experimental subjects.

Tasks like these are typically linked to the experimental hypothesis. The term
demand characteristic refers to an experimental design element that
unintentionally provides subjects with hints about the research hypothesis.
Researchers cannot reveal the research hypothesis to subjects before the
experiment or else they can create a confounding effect (subjects may try to respond
with the correct responses). So knowledge of the experimental hypothesis creates a
confound. This particular confound is known as the demand effect. Demand effect –
occurs when demand characteristics actually affect the dependent variable.

3.1 Experimenter bias and demand effects:

Demand characteristics are aspects of an experiment that demand (encourage) that

the subjects respond in a particular way. Which is a source of systematic error. If
participants recognise the experimenter’s expectation or demand, they are likely to
act in a manner consistent with the experimental treatment. Slight nonverbal cues,
influences from the person administering the experimental procedure like their
presence or actions can affect the subject.

3.2 Reducing demand characteristics:

1) Use an experimental disguise.

The experimental administrator can tell subjects that the purpose of the experiment
is somewhat different from the actual purpose. Most often, experimenters tell
subjects less than the complete ‘truth’ about what is going to happen. Placebo – a
false experimental treatment disguising the fact that no real treatment is
administered. The placebo effect – refers to the corresponding effect in a dependent
variable associated with the physiological impact that goes along with knowledge of
some treatment being administered. For example, when subjects are told that an
energy drink is sold at a discounted price, they believe it is significantly less effective
than when it is sold at the regular, non-discounted price.

2) Isolate experimental subjects.

Researchers should minimise the extent to which subjects are able to talk about the
experimental procedures with each other. Although it may be unintentional,
discussion among subjects may lead them to guess the experimental hypothesis –
which may alter the subject’s responses. Social media can damage the validity of
subject’s responses, as subjects are able to communicate to each other if the
experiment is intended for longer periods of time.

3) Use a blind experimental administrator:

When possible, the research assistant administrating the experiment does not know
the experimental hypothesis themselves. Ignorance can be an advantage in this
case.

4) Administer only one experimental condition per subject:

When subjects observe more than one experimental treatment condition, they are
much more likely to guess the experimental hypothesis. Most researchers should try
avoid administering multiple treatments to an individual subject.

5) Avoid using subjects who are paid based on their performance in the task

Researchers normally pay an incentive for respondent’s cooperation. However,

when the incentive depends on the researcher approving the cooperation of the
individual respondent, and the subjects are aware of this condition, acquiescence
bias creeps in as the subjects become increasingly interested in pleasing the
researcher as the incentive grows larger.

3.3 Establishing control:

The major difference between experimental research and descriptive research is an

experimenter’s ability to control variables by either holding conditions constant or
manipulating the experimental variable. Constancy of conditions – means that
subjects in all experimental groups are exposed to identical conditions except for the
differing experimental treatments. Counterbalancing – attempts to eliminate the
confounding effects of order of presentation by requiring that one fourth of the
subjects be exposed to treatment A first, one fourth to treatment B, one fourth to
treatment C, and finally one fourth to treatment D first.

3.4 Basic VS Factorial experimental design:

In basic experimental designs a single independent variable is manipulated to
observe its effects on a single dependent variable. However, we know multiple
factors influence complex marketing dependent variables like recommendations,
sales, product usage and preferences. Factorial experimental designs are more
sophisticated than basic experimental designs and allow for an investigation of the
interaction of two or more independent variables.

3.5 Laboratory experiments:

In a laboratory experiment the researcher maximises control over the research

setting and extraneous variables. For example, advertising researchers recruit
subjects and bring them to the agency office or perhaps a mobile units designed for
research purposes. Tachistoscope – a device that controls the amount of time a
subject is exposed to a visual image. For example, an advertising and packaging.

3.6 Field experiments:

Field experiments are research projects involving experimental manipulations

implemented in a natural environment. They can be useful in fine-tuning marketing
strategies marketing strategies and determining sales forecasts for different
marketing mix designs.

3.6 Advantages of Between-subjects designs:

A basic question faced by the researchers involves how many treatments a subject
should receive. Two designs discussed: ‘Within-subjects design’ involves repeated
measures because with each treatment the same subject is measured. ‘Between-
subjects design’ – each subject receives only one treatment condition. The design is
usually advantageous although they are usually more costly. The validity between-
subjects designs is higher because by applying only one treatment combination to
one subject, the researcher reduces demand characteristics greatly.

4. Weigh the trade-off between internal and external validity:

5. Recognise the appropriate uses of test marketing
6. Avoid unethical experimental practises