Experimental design

• Experimental design


  The different ways in which the testing of participants can be organised in relation to the experimental conditions
• Types of experimental design

  Independent groups design

  Repeated measures

  Matched pairs
• Independent groups


  Ppts are allocated to different groups where each group represents one experimental condition
• Repeated measures 


  All ppts take part in all conditions of the experiment (may cause order effects/demand characteristics)
• Matched pairs


  Pairs of ppts are matched on variables that may affect the dv. One member is assigned to condition A, other condition B
• Counterbalancing


  Attempts to control for order effects in a repeated measures design (half experience one condition in one order, other for the opposite order) ABBA approach
• Independent groups eval


  • :( Issues with independent differences (ppts aren't the same) which may have an effect on the DV more than IV
  • :) Random allocation can be used to counter this issue, ppts all have an equal chance of being chosen for one condition as any other
  • :( Less economical than repeated measures, ppts only contribute a single result only meaning twice as many ppts are required to produce equivalent data
  • :) Order effects are not a problem, less likely to guess aims
• Repeated measures limitation

  • :( Order effects, order is a confounding variable
  • ppts must do at least two tasks and the order of these may effect their performance and behaviour within the study (e.g. ppts may get bored decreasing performance on second task or opposite)
  • :( High risk of demand characteristics, ppts are likely to work out aims of study through experiencing both conditions which may alter their behaviour/engagement in study. Could distort final results and conclusions made
• Repeated measures strength


  • :) Participant variables are controlled (such as individual differences as ppts are in both conditions), fewer ppts needed =economic benefit
• Matched pairs eval


  • :) Order effects less of a problem, only one ppt per condition
  • :( Ppts can never be matched on variables exactly, therefore ppt variables may still be a problem but less than other options. Therefore there will still be differences that may affect the DV
  • :( Time-consuming and expensive to match ppts on a variable, therefore less economical