research methods- experimental designs Flashcards
independant groups
-one group does condition A and a second group does condition B
-p’s should be randomly allocated to experimental groups
evaluation of independent groups
+no order effects
+will not guess aim
-participant variables
-less economical
ao3 of independent groups: no order effects
-p’s are only tested once so can’t practice or become bored/tired
-controls an important CV
ao3 of independent groups: will not guess aim
-p’s only tested once so are unlikely to guess the research aims
-therefore behaviour may be more ‘natural’ (higher realism)
ao3 of independent groups: participant variables
-p’s in the two groups are different, acting as EV/CV
-may reduce the validity of the study
ao3 of independent groups: less economical
-need twice as many p’s as repeated measures for the same data
-more time spent recruiting which is expensive
repeated measures
same participants take part in all conditions of experiment
evaluation of repeated measures
+participant variables
+fewer participants
-order effects
-participants guess aims
ao3 of repeated measures: participant variables
-person in both conditions has the same characteristics
-controls an important CV
ao3 of repeated measures: fewer participants
-half no. of p’s is needed than in independent groups
-less time spent recruiting p’s
ao3 of repeated measures: order effects are a problem
-p’s may do better or worse when doing a similar task twice. also practice/ fatigue effects
-reduces the validity of the results
ao3 of repeated measures: participants guess aims
-p’s may change their behaviour
-may reduce the validity of the results
matched pairs
-two groups of p’s used but they’re related to eachother based on being paired on participant variable(s) that matter for the experiment
evaluation of matched pairs
+participant variables
+no order effects
-matching is not perfect
-more participants
ao3 of matched pairs: participant variables
-p’s matched on a variable that is relevant to the experiment
-controls participant variables and enhances the validity of the results