Ch. 8 - Experimental Design Flashcards
Using any experimental design involves 3 broad steps…
- Obtaining two equivalent groups of participants
- Introducing the independent variable (operationally define the independent variable)
- Measuring the effect of the independent variable on the dependent variable (operationally define the dependent variable)
Selection differences
The people selected to be in the conditions should not differ in any systematic way
What are the 3 ways to assign participants to experimental conditions so that groups are equivalent?
- Independent groups design
- Groups are made equivalent by randomly assigning participants to experience only one of the conditions of the independent variable - Repeated measures design
- Participants are assigned to participate in all levels of the independent variable - Matched pairs design
- Makes groups equivalent by first selecting pairs of participants who score the same (ie. are matched) on some variable of interest, and then uses random assignment within each pair to determine which participant will experience which level of the independent variable
Mortality
- The dropout factor in experiments
- Poses a threat to internal validity
- Dropout is most likely to happen in studies that last over a long period of time
Repeated measures design (AKA within subjects design)
- To ensure that groups are equivalent is to have the SAME individuals participate in all conditions
- Participants are measured on the dependent variable after being in each condition of the experiment
Advantages and disadvantages of repeated measures design
Advantages:
- Fewer research participants are needed because everyone participates in all conditions
- Extremely sensitive to detecting differences between levels of the independent variable
Disadvantages:
-The different conditions must be presented in a particular sequence, to eliminate sequence as a confounding variable
-
Order effect
-The order of presenting the treatment affects the dependent variable
Types of order effects
- Practice effect = occurs when performance improves because of repeated practice with a task
- Fatigue effect = occurs when performance worsens as participants become tired, bored, or distracted
- Contrast effect = occurs when the response to the second condition in the experiment is altered because the two conditions are contrasted to one another
Two ways to deal with order effects
- Using counterbalancing techniques
2. Ensuring the time between conditions is long enough to minimize the influence of the first condition on the second
Complete counterbalancing
- All possible orders of presentation are included in the experiment
- With 2 levels –> 2! factorial = 2x1 = 2 conditions
- With 3 levels –> 3! factorial = 3x2x1 = 6 conditions
- With 4 levels –> 4! factorial = 4x3x2x1 = 24 conditions
Partial counterbalancing
- Construct a LATIN SQUARE –> a limited set of orders constructed to ensure that:
1) each condition appears at each ordinal position (ie. first, second, third, etc)
2) each condition precedes and follows each condition once
-The number of orders in a Latin square is equal to the number of conditions; for example, if there are 4 repeated measures conditions, there are 4 orders
Matched pairs design
- Instead of simply randomly assigning participants to groups, the goal is to first match people on a crucial participant characteristic
- The matching variable will be either the dependent variable itself or another variable that is strongly related to it
- Matching is most likely to be used when there’s only a few participants available or when it is costly to run large numbers of people in the experiment
- This design can be costly and time consuming though because it requires measuring participants on the matching variable(s) prior to the experiment, or recruiting both members of identical twin pairs for example
