Experimental designs

• Independent groups

  Two separate groups of participants experience two different conditions of the experiment. The performance of the two groups are then compared.

  • Participant variables is an issue
  • Random allocation is used
  • Less economical than RM
  • Order effects are not a problem
• Repeated measures

  All participants experience both conditions of the experiment. The mean scores from both conditions are then compared to see if there is a difference.

  • Order effects - betting better or worse (practice and boredom/fatigue)
  • Counterbalancing is used
  • Participants may work out the aim of the study - demand characteristics ('please-u'/'screw-u')
  • Participant variables are controlled
  • More economical
• Matched pairs

  Participants are paired together on a variable or variables relevant to the experiment e.g. participants may be matched on their IQ for a memory study. This is an attempt to account for participant variables. A pre-test is often used.

  • Participants only do one condition - order effects and demand characteristics are less of a problem
  • Participants can never be matched exactly
  • Matching may be expensive and time-consuming - less economical
• Random allocation

  Random allocation attempts to use evenly distribute participant characteristics across the conditions of the experiment using random techniques. For example, lottery methods (writing names on paper and drawing out of a container).
• Counterbalancing

  Counterbalancing is an attempt to control order effects in a repeated measures design. Half the participants take part in condition A then B and the other half take part in condition B then A. Counterbalancing is sometimes referred to as the ABBA technique. It does not completely remove order effects but it attempts to balance out the effects.