CHAPTER 10: BETWEEN SUBJECTS – FACTORIAL DESIGNS
-More Than One Independent Variable
- Laying Out a Factorial Design
-A Research Example
-Choosing a Between-Subjects Design
• MORE THAN ONE INDEPENDENT VARIABLE:
A factor is an independent variable. The independent variables in these factorial designs. Each
factor will have two or more values or levels.
A factorial design contains more than one independent variable. Designs in which we study two
or more IV at the same time.When we want to explore more than one IV in the same experiment,
we use a factorial design.
Ex. The effect of psychotherapy (IV1 ) and antidepressant drugs (IV2) on depression (DV).
A two factor experiment is the simplest factorial design. The simplest factorial design has only
two factors and is called a two-factor experiment. The results we got from a factorial experiment
gives us two kinds of information.
A factorial design can provide information about both treatment and interaction effects.
Looking for main effect:
A main effect is the action of a single IV on the DV. There can be as many main effects as
independent variables. They gives us information about the effects of each independent variable
in the experiment, called main effects. They also enables us to answer this question: How does
the influence of one IV affect the influence of another in the experiment?
When we measure a main effect, we are asking how much did the change in this one IV change
subject’s behavior? It is simply a change in behavior associated with a change in the value of a
single IV within the experiment.
(When more than one IV exists, each one has a main effect. There are as many main effects as
there are factors.)
To tell if they might or not be important enough to be statistically significant, we need to carry
out the appropriate statistical tests, such as ANALYSIS OF VARIANCE (ANOVA).
*Provide an example of a main effect in a hypothetical study of exercise and depression.
An experimenter studies the effects of exercise intensity (IV1 ) and duration (IV2 ) on depression
(DV). If exercise intensity or duration separately reduced depression, these would constitute
main effects.
*How do we determine whether we have main effects in our experiment?
Perform an appropriate statistical test. (to determine if one or both factors produced significant
main effects / whether the two factors operate independently or not.)
(When we compute statistical tests for factorial experiments, we first evaluate the separate
impactof each IV in the experiment. We test whether eachmain effect is statistically significant
or not.)
Ex: Our plant study, would have two factors - talking and music. We would want to know the
main factors of both factors. A factorial experiment allows us to know if each factor alone
produces a significant effect on behavior.
Factor 1: How much did changes in talking affect plant growth?
Factor 2: How much did changes in music affect plant growth?
* In a 2 x 3 x 3 study, how many IVs and treatment conditions are there?
There are 3 independent variables and 18 treatment conditions.
*Provide an example of a 2 x 3 x 3 study.
The independent variables were the perpetrator’s gender (male or female), relationship to the
child (parent, step-parent, or parent’s partner), and severity of the abuse (neurological damage,
broken bones, or bruising). The dependent variable was sentence length.
Looking for Interactions:
An interaction is the joint effect of two or more IVs on the DV. When the effects of one factor
depend on another factor.
When there is an interaction, the effect of one IV is different across levels of the other IV. /
Interaction is present if one independent variable changes across the levels of another
independent variable.
( whenever an interaction is present in a two-factor experiment, we CANNOT get a complete
picture of the results of the experiment without considering both factors because the effects of
one factor will change depending on the levels of the other.)
The presence of an interaction between 2 factors also tells us that the main effects of one factor
will be altered by the other factor; their effects will depend on which levels of both factors we
are interpreting. An interaction tells us that there could be limits or exceptions to the main effects
of one or more factors, thus we say that an interaction qualifies the main effects.
*Provide an example of an interaction.
If the antidepressant Paxil produced greater reductions in depression in the Cognitive Behavior
Therapy (CBT) condition than the Waiting List condition, this would illustrate an interaction
between drug and psychotherapy.
A higher-order interaction is an interaction among three or more IVs.
Interpretation can be difficult when more than three IVs interact in an experiment.
* Provide an example of a higher-order interaction.
A previous hypothetical study examined the effect of a perpetrator’s gender (male or female),
relationship to the child (parent, step-parent, or parent’s partner), and severity of the abuse
(neurological damage, broken bones, or bruising) on sentencing.
There would be a higher-order interaction if the perpetrator’s gender, relationship to the child,
and severity of abuse jointly determined sentence length.
When there are more than two independent variables in a factorial experiment, the picture
becomes more complex; we can get higher-order interactions that involve more than two
variables at a time. In a three-factor experiment it is possible to get an interaction among all
three independent variables.
( The action of each factor could be influenced by the values of the other two. Driver experience,
alcohol and degree of darkness for example interact in causing traffic accidents. In an experiment
with three independent variables it is also possible that any two factors but not the third could
interrupt just as they might in a 2 factor experiment.)
* How many interactions are possible in a study with three IVs?
Assign letters (A, B, C) to the independent variables. Identify all unique two- and three treatment
combinations. For three independent variables, these include AB, AC, BC, and ABC. ABC is the
higher-order interaction.
*How does an interaction affect the interpretation of our results?
An interaction qualifies a main effect, warning us that there may be limits or exceptions to the
effect of an IV on the DV. When there is an interaction, we must consider both IVs, because the
effects of one factor will depend on the levels of the other factor.
• LAYING OUT A FACTORIAL DESIGN:
The factor-labeling method lists the two factors in parentheses after the numerical notation. For
example, 2 x 2 (Type of Name x Length of Name).
This method lists the two factors and their respective levels after the numerical notation. For
example, 2 x 2 (Type of Name: given, nickname x Length of Name: short, long).
*What advantage does the factor and levels method have over the factor-labeling method?
The factor and levels method provides more detailed information about the design than the
factor-labeling method.
• A RESEARCH EXAMPLE:
*Why use a factorial design instead of two separate univariate experiments?
A factorial design is more efficient since it combines several one-factor experiments and allows
us to study interactions. A factorial design can achieve greater external validity since it can better
recreate the complexity of the multivariate environment.
• CHOOSING BETWEEN SUBJECT – DESIGNS:
*Why should we keep between-subjects designs simple?
Practical limitations include:
• number of subjects
• time
• interpretability of results
