experimental design

• the 3 different types of experimental design are: repeated measures design, independent groups design and matches pairs design
• repeated measures design is when all participants receive all levels of the IV e.g. each participant does the task w/ the TV on for the memory test, and then maybe a week later each participant does a similar test w/o the TV on, you then compare the performance (DV) of the participants on the 2 tests
• independent groups design is when participants are placed in separate (independent) groups , each group does one level of the IV e.g. group A does the task w/ the TV on (1 level of the IV), then Group B does the task w/ no TV (the other level of the IV), we compare the performance (DV) of the 2 groups
• matched pairs design is when the compromise is to use 2 participants but match participants on key characteristics believed to affect performance on the DV (e.g. IQ or time spent watching TV)
• matched pairs design: then 1 member of the pair is allocated to Group A and the other to Group B, the procedure is then the same as for independent groups
• matched pairs design: it is important to realise that the characteristics for matching must be relevant to the study, in order words you wouldn't need to match participants on gender if you were testing memory unless there was some evidence that gender was a potential confounding variable
• limitation of repeated measures design: the order of the conditions may affect performance (an order effect) e.g. participants may do better on the 2nd test because of a practice effect or because they are less anxious, in some situations participants may do worse on the 2nd test because of being bored w/ doing the same test again (boredom effect)
• limitation of repeated measures design: when participants do the 2nd test they may guess the purpose of the experiment which may affect their behaviour, e.g. some participants may purposely do worse on the 2nd test because they want it to appear as it they work less well in the afternoon
• limitation of independent groups design: the researcher can't control the effects of participant variables (i.e. the different abilities or characteristics of each participant) e.g. participants in Group A might happen to have better memories than those in Group B this would act as a confounding variable
• limitation of independent groups design: independent groups design needs more participants than repeated measures design in order to end up w/ the same amount of data
• limitation of matched pairs design: it is very time consuming and difficult to match participants on key variables, the researcher probably has to start w/ a large group of participants to ensure they can obtain matched pairs on key variables
• limitation of matched pairs design: it is not possible to control all participant variables because you can only match on variables known to be relevant but it could be that others are important e.g. in a memory experiment you might match on memory abilities but later find that some of participants had been involved in a teaching programme to boost memory skills and you should have matched on this
• dealing w/ the limitation - repeated: researchers may use 2 different tests to reduce a practice effect though the 2 tests must be equivalent, this can be done by constructing a test of say 40 items and randomly allocating items to Test A and Test B
• dealing w/ the limitation - repeated: the main way that order effects are dealt w/ is using counterbalancing, in order to avoid participants guessing the aims of a study a cover story can be presented about the purpose of the test
• dealing w/ the limitation - independent: randomly allocate participates to conditions which (theoretically) distribute participants variables evenly
• dealing w/ the limitation - independent: random allocation can be done by putting the participants names in a hat and drawing out the names so that every person goes in Group A
• dealing w/ the limitation - matched: restrict the number of variables to match on to make it easier
• dealing w/ the limitation - matched: conduct a pilot study to consider key variables that might be important when matching
• evaluation - independent S: participants are less likely to guess the aim and change their behaviour accordingly
• evaluation - independent L: as the groups contain different people, their individual differences might influence the results
• evaluation - repeated S: by using the same participants in all conditions there are no individual differences to act as a confounding variable
• evaluation - repeated L: by doing this experiment more than once in difference conditions that participants may be affected by order effects
• evaluation - matched S: by matching the groups in each condition on key participant variables the influence of individual differences should be significantly reduced
• evaluation - matched L: despite some control it is impossible to remove all individual differences
• counterbalancing: ensures that each condition in a repeated measures design is tested first or second in equal amounts
• counterbalancing: if participants do the same memory test first in the morning and then in the afternoon we might expect them to do better on the second test because they have had some practice or they might do worse because they are bored w/ the task
• counterbalancing: these are called order effects which can be dealt w/ using counterbalancing
• counterbalancing: there are 2 ways to counterbalance order effects in each case we have 2 conditions = condition A = test done in the morning, condition B = test done in the afternoon
• way 1: divide participants into 2 groups = group 1 each participant does A then B, group 2 each participant does B then A
• way 1: note that this is still a repeated measures design even though there are 2 groups of participants, because comparison will be made for each participant on their performance on the 2 conditions (morning and afternoon)
• way 2: this time all participants take part in each condition twice = trial 1 = condition A (morning), trial 2 = condition B (afternoon), trial 3 = condition B (afternoon) and trial 4 = condition A (morning)
• way 2: then we compare scores on trials 1 and 4 w/ trials 2 and 3, as before this is still a repeated measures design because we are comparing the scores of the same person
• in a repeated measures design there are 2 (or more) levels of the IV, each level is called a 'condition' instead of levels there may be en experimental condition and a control condition
• in an independent groups or matched pairs design each group does 1 condition - the experimental group does the experimental condition and the control group does the control condition