Experimental designs

• Experimental design


  Different ways in which participants are organised in relation to experimental conditions.
• Independent groups design

  • Participants are allocate to different groups, where each group represents one experimental condition.
  • 2 separate groups
  • 2 separate conditions
  • Participants only experience 1 IV
  • Performance of each group is compared.
• Repeated measures

  • All participants take part in all conditions of the experiment.
  • All participants experience condition A.
  • All participants experience condition B.
  • Means from both conditions would be compared to see if there was a difference.
• Matched pairs design

  • Pairs of participants are matched on some variables that may effect the dependent variable.
  • E.g age
  • Then one member of the pairs is assigned to condition A and one to condition B.
  • E.g in a memory study, participants may be matched on IQ, as this may indicate their ability to recall information.
  • Controls confounding variables and participant variables.
• Evaluation of independent groups design

  • Participant variables between groups may act as a confounding variable, reducing the validity of findings. Using random allocation deals with this.
  • Less economical, twice as many participants needed than that of repeated measures, so increases time and money spent on recruiting participants.
  • Order effects are not a problem, so participants are less likely to guess the aim.
• Evaluation of repeated measures design

  • Order effects, participants have to be in both conditions. Repeating tasks may create boredom or fatigue that may cause deterioration in second condition. Or participants may improve through practice. Order effects acts as a confounding variable and can be controlled using counterbalancing.
  • Demand characteristics, as participants are exposed to both conditions so they are likely to guess the aim.
  • Control of participant variables: Higher validity, fewer participants are needed, so more economical (less time spent recruiting them).
• Counter balancing

  An attempt to control order effect in repeated measures.

  • Half participants experience conditions in one order, and other half of participants experience conditions in other order.
• Random allocation

  An attempt to control participant variables in independent groups design which ensures each participant has the same chance of being in either group.
• Evaluation of matched pairs design

  • Order effects and demand characteristics are less of a problem as participant only take part in one condition.
  • Matching may be time consuming and expensive, particularly if pre-test is required, so less economical than other designs.
  • Participants cannot be matched exactly, so reduction in internal validity.