Experimental Design

Cards (10)

  • how you allocate your participants to the varying conditions of your experiment
  • independent groups

    participant only takes part in 1 level of the IV
    -IV naturally occurring(gender/age), must use design
    -randomly allocated to one level of IV (equal chance)
  • strengths of independent groups
    -only take part in one condition, less likely to guess aim of study, reducing effects of demand characteristics
    -no order effects that can reduce validity of findings
  • weakness of independent groups
    -problem with participant variables affecting DV rather IV (personality)
    -more participants required for type of design compared to repeated measures
  • repeated measures

    -participant takes part in all levels of the IV
    -cannot be used if IV is naturally occurring
    -must be counterbalancing (ABBA design)
  • strengths of repeated measures
    -design eliminates any effect of participant variables, as all participants take part in all conditions (controlled)
    -fewer participants required than independent groups
  • weakness of repeated measures
    -take part in all conditions, chance of demand characteristics affecting the study (work out aim behave in way to fulfill rather than true behavior)
    -other effects affect findings and reduce validity
    • practice effect: get better at task completed similar one
    • fatigue effect: more taskes do more tired become
    • boredom effect: repeating similar tasks bore participants
  • matched pairs

    -participants are matched on a variable researches wish to control (gender, age, ethnicity)
  • strengths of matched pairs
    -participant variables controlled and eliminated, as participants have been matched
    • psych can be more confident IV is affecting Dv rather than participant variables
  • weakness of matched pairs
    -find participants who are matched on all variables (time consuming)
    -may be one or two participant variables that are overlooked with initial matched (could affect DV rather than IV)
    -cannot control every participant variable