Experimental design

• What is an experimental design?

  Refers to how participants are allocated to the different conditions in an experiment.
• What are the 3 types of experimental design?

  1. Independent groups

  2. Repeated measures

  3. Matched pairs
• Define ''independent groups''

  Participants are allocated to just one experimental condition
• Define ''repeated measures''

  All participants take part in all experimental conditions
• Define ''matched pairs''

  Participants paired on a variable and then one of each pair allocated to each experimental condition
• What are order effects?

  - Occur in repeated measures design

  - Repeating 2 tasks could create boredom or fatigue leading to deterioration in performance on 2nd task

  - Or could lead to practice effects where participants' performance improves
• What is counterbalancing?

  - An experimental technique used to overcome order effects in a repeated measures design

  - Half the participants experience the conditions in one order and the other half in the opposite order (A-B then B-A)

  - Ensures that each condition is tested first or second in equal amounts.
• Give two advantages of independent groups design

  1. No order effects

  2. Less demand characteristics (less likely to guess aim)
• Give two disadvantages of independent groups design

  1. Participants variables are not controlled for (have bigger impact on results)

  2. Need more participants
• Give two disadvantages of repeated measures design

  1. More demand characteristics

  2. Order effects - boredom/fatigue or practice effects
• Give two advantages of repeated measures design

  1. Participants variables are controlled for

  2. Less participants needed
• Give two advantages of matched pairs design

  1. Less likely to have demand characteristics + order effects

  2. Reduces influence of participant variables
• Give two disadvantages of matched pairs design

  1. Less economical + time-consuming

  2. Not possible to control all participant variables as can only match on variables known to be relevant, but others could be important
• Give one way to overcome order effects in a repeated measures design

  Counterbalancing (A-B, B-A) - whereby you split the sample in half - one half does task A and then B and the other half does task B then A
• Given one way to overcome disadvantages of independent groups

  Random allocation
• Given one way to overcome disadvantages of matched pairs

  1. Restrict the number of variables to match on to make it easier

  2. Conduct a pilot study to consider key variables that might be important when matching