Summary Consumer Psychology
Lecture/Tutorial 1 – Research
Fundamentals
Descriptive research is not causal and cannot draw any causal conclusions. The relationships are only
correlations not causalities. You need an experiment to draw causal conclusions.
Example descriptive research:
Experiment: the process of manipulating one or more independent variables and measuring their
effect on one or more dependent variables, while controlling for the extraneous variables.
Experimental design: the set
of experimental procedures
specifying the test units and
sampling procedures,
independent variables,
dependent variables and
how to control the extraneous
variables.
Causality: When the occurrence of X increases the probability of the occurrence of Y. The
relationship between cause and effect tends to be probabilistic. Moreover, we can never prove
causality, we can only infer a cause-effect relationship.
Conditions for causality: these conditions are necessary but not sufficient to demonstrate causality.
1. Concomitant variation: A condition for inferring causality that requires that a cause, X and
an effect, Y, occur together or vary together as predicted by the hypothesis under
consideration.
2. Time order of occurrence of variables: it states that the causing event must occur either
before or simultaneously with the effect, it cannot occur afterwards.
3. Elimination of other possible causal factors: it means that the factor or variable being
investigated should be the only possible causal explanation. We can never confidently rule
out all other causal factors, but with experimental designs we can control for some of the
causal factors.
What are extraneous variables? They influence the effect, but you don’t want them.
Extraneous variables are undesirable variables that influence the relationship between the
variables that an experimenter is examining
1
, They influence the outcome of an experiment, though they are not the variables of interest
These variables are undesirable because they add error to an experiment.
Extraneous variables:
History: Changes that are external to the experiment but occur at the same time; e.g.
promotional campaigns, elections, time of the day, event that happens in society
Maturation: Changes that occur within the subjects during the passage of time. E.g. physical
growth, aging, hunger, change over time.
Testing effects: caused by the process of experimentation. A pre-test has had an effect on
the post-test. It occurs in experiments using repeated testing, subject being tested becomes
knowledgeable about the experiment.
Main testing effect: an effect of testing occurring when a prior observation affects a
latter observation. E.g. when you do a check in the supermarket and the second time
you come back, because the first test was so intrusive, you will buy things that you
thing are healthier/less expensive, therefore the second bill will look different, only
because the subject got measured before.
Interactive testing effect: a subject reacts different to the treatment
Selection bias: it refers to the improper assignment of test units to treatment conditions.
Solution: random assignment.
Instrumentation: it refers to the changes in the measuring instrument, in the observers, or in
the scores themselves. Instrumentation effects are likely when interviewers make pre- and
posttreatment measurements.
Statistical regression: the effects occur when test units with extreme scores move closer to
the average score during the course of the experiment. This has a confounding effect on the
experimental results, because the observed effect (change in attitude) may be attributable to
statistical regression rather than to the treatment (test commercial).
Mortality: it refers to the loss of test units while the experiment is in progress.
Controlling extraneous variables:
Randomization: it refers to random assignment of test units to experimental groups by using
random numbers. Treatment conditions are also randomly assigned to experimental groups.
Might not be effective with small sample sizes. You only make a slight change to the aspect
of interest.
Matching: a potentially influential variable is kept the same for all subjects before assigning
them to treatment conditions. Test units might be similar on the variables selected but
unequal to others.
You need a minimum of 30 people in one group, but you still have a big chance that the
characteristics are not similarly distributed. If that’s the case, you might check some
influential extraneous variables the same for all subjects. E.g. are you on a diet, are you
hungry and divide people on these characteristics.
Statistical control: it involves measuring the extraneous variables and adjusting for their
effects through statistical analysis.
Design control: it involves the use of experiments designed to control specific extraneous
variables.
What would a good experiment look like: You assign people totally random in room A and B.
Characteristics are evenly distributed. Nevertheless, the randomization only works if you have a very
BIG sample size. Only then you can make generalizations.
2
,A classification of experimental designs:
Pre-experimental designs: designs that do not control for extraneous factors by
randomization
True experimental designs: experimental designs distinguished by the fact that the
researcher can randomly assign test units to experimental groups and also randomly assign
treatments to experimental groups.
Quasi-experimental designs: designs that apply part of the procedures of true
experimentation but lack full experimental control.
Statistical designs: designs that allow for the statistical control and analysis of external
variables.
Pre-experimental designs:
o One-shot case study (X O): a single group of test units is exposed to a treatment X, and then
a single measurement on the dependent variable is taken (O). There is no random
assignment of test units.
Problem: There is no comparison level. You can NOT draw conclusions about the effect of
food variety on food intake The one-shot case study is more appropriate for exploratory
than for conclusive research.
Example: does food variety increase food intake?
o One-group pretest-posttest design (O X O): a group of test units is measured twice. There is
no control group.
Problem: Validity of this conclusion is questionable because extraneous variables are largely
uncontrolled. E.g. the difference between O1 and O2 can be attributed to (1) food variety or
(2) situational variables.
Example: does food variety increase food intake?
3
, o Static group design (X – O1 – O2): The experimental group, which is exposed to the
treatment and the control group. Measurements on both groups are made only after the
treatment, and test units are not assigned at random.
Problem: mortality effects and selection bias. Extraneous variables are largely uncontrolled.
The difference in food intake between treatment group and control group can be attributed
to food variety and subject variables.
Example: does food variety increase food intake?
Food variety Food Intake
No food variety
True experimental designs:
Posttest-only control group design (R) X O1 – (R) X O2: Does not involve any
premeasurement. The experimental group is exposed to the treatment, but the control
group is not, and no pretest measure is taken.
Problem: selection bias and mortality, design does not allow the researcher to examine
changes in individual test units.
Advantages: time, cost, sample size requirements.
Example:
Pretest-posttest control group design (R) O1 X O2 – (R) O3 X O4: test units are randomly
assigned to either the experimental or the control group, and a pretreatment measure is
taken on each group. Then, the experimental group is exposed to the treatment (X). Finally, a
posttreatment measure is taken on each of the experimental and control groups.
Problem: interactive testing effect is not controlled.
Solomon four-group design: explicitly control for interactive testing effect, in addition to
controlling for all the other extraneous variables.
Problem: expensive and time-consuming.
4
