Factorial Design Flashcards
What are factorial designs?
Factorial experiments are experiments where multiple independent variables are manipulated.
What is a factor?
Independent variable.
What indicates the levels for a specific independent variable?
The value of the numeral. Ex: 2 x 2 means 2 levels for each variable.
How many conditions?
Multiply each numeral. Ex: 5 x 3 = 15 conditions.
How do we find if there is a main effect?
Calculate the average of each row and column. If the rows or columns are different than there is a main effect.
How do we find if there is an interaction?
From graph: If not parallel than no interaction.
From table: If the difference between each column/row is different then there is an interaction.
What are the types of factorial design? (3)
-Between-subject
-Within-subject
-Mixed design
Pros and Cons of between-group design?
- Cons – Individual differences can become confounding variables, increasing the variance of scores.
- Pros – Avoid order and sequence effects
How do we know it’s between-group design?
All participants are randomly assigned to each group.
How do we know its within-group design?
All participants participate in ALL conditions. (choose this if you know the individual differences will be very large)
Pros and Cons of within- group design.
Cons:
* The number of different treatment conditions can be high and time consuming
* (participant attrition, fatigue/practice)
Pros:
* Fewer individuals needed
* Reduces problems related to individual differences
How do we know its a mixed factorial design?
Effect of manipulations on two groups of individuals. Ex: G1 does A1A2 but only B1 and G2 does A1A2 but only B2.
Pros and Cons of mixed factorial design.
Pros:
* Control for unwanted individual differences, while investigating
specific individual differences
Cons:
* Limits the ability to make causal statements about the relationship
between variables
* Limits internal validity
What are the advantages of factorial design?
- Increases external validity (Generalizations)
- Theories with two or more independent variables can only be
tested via complex factorial designs
What are the disadvantages of factorial design?
- Too many variables can result in: Huge experiments and requirements for multiple conditions.
- Interactions that are not easily interpreted