Chapter 9—Conducting Marketing Experiments
TRUE/FALSE
1. Experimental research attempts to find causal relationships among variables.
2. In an experiment, the researcher manipulates the dependent variable and measures its effect on the
independent variable.
3. Participants in experimental research are typically referred to as respondents.
4. In experimental research, the independent variable is manipulated rather than simply measured.
5. An experimental construct refers to one of the possible levels of an experimental variable
manipulation.
6. Covariates are categorical variables such as a subject’s gender or ethnicity.
7. In an experiment, effects are the characteristics of experiments that allow hypotheses to be tested.
8. Experimental treatment refers to the way an experimental variable is manipulated.
9. Experimental treatments are administered to the control group.
10. The term linkage refers to a specific treatment combination associated with an experimental group.
11. An experiment can have only one independent variable.
12. People are the most common test units in most marketing experiments.
13. Random assignment of subjects to treatment and control groups helps ensure that experimental and
control groups do not differ from each other in important ways at the beginning of a research study.
14. Experiments in which an individual subject is exposed to more than one level of an experimental
treatment are referred to as repeated measures designs.
15. A confound in an experiment means that there is an alternative explanation beyond the experimental
variables for any observed differences in the dependent variable.
16. When subjects guess the purpose of an experiment, this creates a confound known as a bias effect.
17. One way to reduce demand characteristics is to tell subjects the true purpose of the experiment so that
they will be more willing to participate honestly.
18. A confound is an experimental deception involving a false treatment.
19. The people administering an experiment must be aware of the experimental hypotheses.
20. Factorial experimental designs are the least sophisticated type of experimental design.
21. When a test market is conducted in five retail stores in Erie, Pennsylvania, a laboratory experiment has
been performed.
22. Between-subjects designs involve repeated measures because with each treatment the same subject is
measured again.
23. The question as to whether the experimental treatment was the “sole cause” of the changes in the
dependent variable is the basic issue in external validity.
24. A maturation effect is a function of time and the naturally occurring events that coincide with growth
and experience.
25. Test-market sabotage involves intentional attempts to disrupt the results of a test-market being
conducted by another firm.
MULTIPLE CHOICE
1. A researcher is conducting an experiment in which one group of people is exposed to one
advertisement and another group is exposed to another advertisement. Specifically, he is examining the
effect of headline font sizes on consumers’ attitude toward the brand advertised. The participants in
this experimental research are referred to as ____.
a.
respondents
b.
elements
c.
factorials
d.
subjects
2. In experimental research, categorical variables like a subject’s gender or ethnicity are known as ____.
a.
blocking variables
b.
covariates
c.
main variables
d.
confounds
3. Experimental results that show that consumers purchased more when a store had bright blue lights than
they did when the store had bright orange lights. However, when the lighting was low, there was no
difference between blue and orange lights. This illustrates a(n) ____.
a.
filter
b.
interaction
c.
confound
d.
synergy
4. All of the following are experimental design elements EXCEPT for the ____.
a.
selection and assignment of subjects to treatments
b.
control over extraneous variables
c.
manipulation of the independent variable
d.
manipulation of the dependent variable
5. The group receiving the treatment being studied is called the ____.
a.
primary group
b.
experimental group
c.
control group
d.
unit of analysis
6. Which term refers to a treatment combination within an experiment?
a.
level
b.
link
c.
cell
d.
unit
7. If the sampling units in an experimental cell are somehow different than the units in another cell, and
this difference affects the dependent variable, ____ may occur.
a.
systematic error
b.
sampling error
c.
experimenter bias
d.
subject bias
8. A researcher can equally distribute the effects of extraneous variables to all conditions in an
experiment by using ____.
a.
confounding
b.
split sampling
c.
repeated measures
d.
randomization
9. Monica is conducting an experiment in which all subjects see all of the ads she is testing. This type of
experiment, in which an individual subject is exposed to more than one level of an experimental
treatment, is called a ____ design.
a.
between-subjects
b.
repeated measures
c.
redundant manipulation
d.
randomization
10. Which term refers to an alternative explanation beyond the experimental variables for any observed
differences in the dependent variables?
a.
confound
b.
interaction
c.
randomization
d.
repeated measures
11. When the person administering experimental procedures influences the subjects’ behavior or sways
them to slant their answers to cooperate with him or her, ____ has occurred.
a.
experimenter bias
b.
response bias
c.
Type I error
d.
Type II error
12. Demand characteristics can be reduced in a number of ways. Which strategy below is NOT one of
these?
a.
Use an experimental disguise,
b.
Administer multiple experimental treatment levels to each subject.
c.
Use a “blind” experimental administrator.
d.
Isolate experimental subjects.
13. Caroline is participating in an experimental study in which she is taking an herbal supplement and the
researcher measures her perceived energy levels for several weeks. Although she doesn’t know it, the
supplement she is given in the study does not contain the herb of interest. However, Caroline feels as
though she has more energy than before, and she attributes it to the herbal supplement. This effect is
called a(n) ____.
a.
maturation effect
b.
false positive
c.
counterbalancing effect
d.
placebo effect
14. Which term means that subjects in all experimental groups are exposed to identical conditions except
for the differing experimental treatments?
a.
the Hawthorne effect
b.
confounding
c.
constancy of conditions
d.
compounding
15. A food company tests a new product by having one group of subjects taste their own product first and
then taste a competitor’s product second, while a second group of experimental subjects tastes the
competitor’s product first followed by the company’s own product. Which type of experimental design
is being used?
a.
counterbalanced
b.
reversed
c.
confounded
d.
validated
16. Which experimental design involves manipulating a single independent variable to observe its effect
on a single dependent variable?
a.
primary experimental design
b.
basic experimental design
c.
factorial experimental design
d.
counterbalanced experimental design
17. Research projects involving experimental manipulations that are implemented in a natural environment
are called ____.
a.
laboratory experiments
b.
field experiments
c.
primary experiments
d.
secondary experiments
18. Which experimental research design involves repeated measures?
a.
within-subjects design
b.
between-subjects design
c.
squared-subjects design
d.
interdependent-subjects design
19. In which experimental research design does each subject receive only one treatment combination?
a.
within-subjects design
b.
between-subjects design
c.
squared-subjects design
d.
independent-subjects design
20. The question as to whether the independent variable was the sole cause of the change in the dependent
variable is the basic issue in ____.
a.
a repeated measures study
b.
internal validity
c.
a matching study
d.
external validity
21. The test of an experimental manipulation to intended make sure that the manipulation does produce
desired differences in the independent variable is called a ____.
a.
manipulation check
b.
reliability assessment
c.
factor analysis
d.
surrogate manipulation
22. When a competitor introduces a 15 percent price cut in order to blunt the effect of a test marketing
study, a ____ effect has occurred.
a.
maturation
b.
testing
c.
history
d.
cohort
23. The change in the dependent variable that occurs because members of one experimental group
experienced different historical situations than members of other experimental groups is called a(n)
____.
a.
cohort effect
b.
Hawthorne effect
c.
testing effect
d.
instrumentation effect
24. Which type of effect is a function of time and the naturally occurring events that coincide with growth
and experience?
a.
history effect
b.
testing effect
c.
selection effect
d.
maturation effect
25. Salespeople are tested one year after a sales training program and perform better on the exam, not
because of the training program, but because they have gained one year’s experience in sales. Which
type of effect has occurred?
a.
selection effect
b.
maturation effect
c.
history effect
d.
cohort effect
26. A set of high school students who take the ACT in their junior year perform better on that exam during
their senior year because they know better how to take the exam due to what they experienced on the
first exam. This is an example of a(n) ____.
a.
mortality effect
b.
testing effect
c.
history effect
d.
instrumentation effect
27. In a certain study, different interviewers are used in a pretest from those used in the posttest and this
produces different results in the study. This is an example of a(n) ____.
a.
history effect
b.
mortality effect
c.
instrumentation effect
d.
cohort effect
28. When a change in the wording of questions, a change in interviewers, or a change in other procedures
causes a change in the dependent variable, a(n) ____ effect has occurred.
a.
instrumentation
b.
redundancy
c.
cohort
d.
attrition
29. When some subjects stop participating in an experiment before it is completed, affecting the results of
the study, a(n) ____ effect has occurred.
a.
mortality
b.
history
c.
instrumentation
d.
confounding
30. When a researcher claims that the results of a test market in Indianapolis, Indiana will hold in a
national rollout of the new product, this researcher is claiming ____.
a.
internal validity
b.
the repeated measures effect
c.
constant error
d.
external validity
1. In an experiment, the ____________________ variable is manipulated and its effect is measured on
the ____________________ variable.
2. In an experiment, change in the ____________________ variable is presumed to be the cause of the
results.
3. A continuous variable that is expected to show a statistical relationship with the dependent variables is
called a(n) ____________________.
4. A difference in means between the different levels of any single experimental variable is referred to as
a(n) ____________________.
5. In an experiment, the ____________________ group does not receive the experimental treatment.
6. When subjects in the experimental group are administered the treatment in the afternoon while the
subjects in the control group participate in the experiment in the morning, it is likely to result in
____________________ error.
7. ____________________ is intended to equally distribute the effects of extraneous variables to all
conditions.
8. An experimental design element of procedure that unintentionally provides subjects with hints about
the research hypothesis a called a(n) ____________________.
9. When the experimenter’s comments influence the subjects’ behavior so that they give answers that
they think the experimenter wants to hear rather than their true feelings, we say that
____________________ has occurred.
10. When the psychological impact that goes along with belier that a treatment has been administered
affects the dependent variable but, in reality, no treatment has been administered, the
____________________ effect has occurred.
11. A(n) ____________________ is an experimental deception that involves a false treatment.
12. When subjects in all experimental groups are exposed to identical conditions except for the differing
experimental treatments, we say that ____________________ has been achieved.
13. A research organization conducts a taste test in its offices located in a shopping mall. These taste tests
are best termed a(n) ____________________ experiment.
14. When Procter & Gamble test markets a new shampoo to consumers in Kansas City and St. Louis, the
consumers are participating in a(n) ____________________ experiment.
15. A(n) ____________________ effect is a nuisance effect occurring when the initial measurement or
test alerts or primes subjects in a way that affects their response to the experimental treatments.
ESSAY
1. List the four important elements in experimental design.
2. Explain how systematic or nonsampling error occurs in experiments and discuss ways to minimize it.
3. What are demand characteristics and why are they a concern for researchers? Discuss four ways of
reducing demand characteristics.
4. Explain the advantages of a between-subjects experimental design over a within-subjects design.
5. Compare and contrast internal validity and external validity and discuss which one is most important
in experimental research.