Experimental Designs

Cards (9)

  • Experimental designs:
    • as well as knowing how the experiment is being conducted, a researcher needs to decide whcih experimental design is being used
    • this is the decision about how to allocate participants to different conditions
    • there are 3 experimental designs: independent measures, repeated measures and matched pairs design
  • Independent measures design
    an independent measures design involves using different people in each condition
  • Evaluation of independent measures design
    S - no order effects
    S - reduced demand characteristics
    W - individual differences
  • Repeated measures design
    a repeated measures design involves using the same people in each condition. Each participant takes part in both/all conditions
  • Evaluation of repeated measures design
    S - no individual differences
    W - order effects
    W - increased demand characteristics
  • Order effects
    some investigations will use the same participants in each condition - a repeated measures design. A problem with this is that the particpants may endure the 'fatigue effect' or the 'practice effect'. These are collectively known as 'order effects' as they are caused by the order in which participants complete the conditions
  • Counterbalancing
    to control for order effects you can do something called counterbalancing. This is sometimes known as the 'ABBA method'
    • half the participants take part in condition A and then complete condition B
    • half the participants take part in condition B and then complete condition A
    this way, it means that if there are any practice effects or fatigue effects then the ordering of the groups cancels this out
  • Matched pairs design
    matched pairs involves using different participants in each condition, but participants are 'matched' or paired with another who is similar in a number of variables
  • Evaluation of matched pairs design
    S - reduced individual differences
    S - reduced demand characteristics and no order effects
    W - there are still some participant variables