Experimental designs

Cards (9)

  • Repeated measures design:
    • Each participant takes part in every condition under test.
    • Each condition represents one level of the Independent variable
    • there may also be a control condition
  • independent measures design:
    • Participants are allocated to two (or more) experimental groups representing different levels of the IV.
    • There may also be a control group
  • Matched participants design:
    • Participants who are similar on key variables (eg memory ability, age) are paired. One member of the pair is placed in group A and the others in group B.
    • This means there are two groups of participants. Each group is given one level of the IV.
  • Positive of Repeated measures:
    + Good control of participant variables , since same person is tested twice.
    + Fewer participants needed than in the independent measures design.
  • Negative of repeated measures:
    - Practice effect. Student may be better and had adapted from the first condition.
    - Participants may guess the purpose of the experiment.
    - condition A may be easier than condition B
  • Independent measure positives:
    • Avoids order effects because each participant is only tested once.
    • Avoids participants guessing the aims of the experiment
  • Negatives of Independent measures design:
    - No control of participant variables. Participants in group A may be more intelligent that is why group A had higher on the test than group B.
    - Needs more participants than repeated measures design. If there is 20, they will be split between the two groups. And collect data only for 10 people.
  • matched participants positive:
    + Acts as a control for participant variables because of the matching (like repeated measures)
    + Avoids order effects because it is like an independent measures design.
  • Matched participants negative:
    - Very time consuming to match participants on key variables
    - May not control all participant variables because you can only match on variables known to be relevant, but it could be that other variables are important.