In the study of Psychology there are three experimental designs that are typically used. An experimental design is the way in which the participants are used across the different conditions in a laboratory experiment. In a laboratory experiment there is always one control condition (this is a group of participants matched as closely as possible to the experimental group that don’t receive the IV. They act as a baseline to compare against the experimental group), along with one or more experimental conditions. Researchers have to decide whether or not they want to use the same or different participants in the control and the experimental condition.
There are three experimental designs that a researcher can use.
(1) Independent Measures this is when a researcher uses participants once in either the control condition or the experimental condition.
(2)Repeated Measures this is when participants are used in each condition, both the control condition and the experimental condition(s).
(3)Matched Pairs this is when participants take part in only one condition (either the control or the experimental condition), however, participants are matched in terms of certain characteristics that may affect the outcome of the study, (for example, in a study looking at memory performance, participants across the control and the experimental condition could be matched in terms of age due to the fact that age can have an effect on memory performance).
Exam Tip: In the exam, you need to be able to outline each experimental design in terms of how the participants are used, in addition, you also need to be able to look at a description of research and suggest what experimental design a researcher would be best using. The best way to justify the choice of experimental design is to know two strengths and two weaknesses of each design.
Evaluation of the 3 Experimental Designs:
Revising the evaluation of the three experimental designs can be made easy by learning the following items and by being able to apply these items as either a strength or weakness for each of the designs.
(1) The number of participants required for a study (the less participants required in a study the better. It can be quite difficult for researchers to obtain participants for their study especially if funding is limited and the researcher is unable to pay the participants for taking part in their research). This can be seen to be a strength of the repeated measures design less participants are needed as each participant takes place in both the control and the experimental condition. However, this can be seen to be a weakness of the independent measures design as participants only take part in one condition meaning that twice as many participants are needed to take part in a study where there is a control and experimental condition.
(2) Participant variables everybody is unique and different. Remember, when conducting research, the experimenter wants the only differences between the experimental and control condition to be the manipulation of the independent variable. If we use different participants in the control and experimental condition, not only is the IV different across these two conditions, a potential extraneous variable (EV) is introduced in that there are participant differences. Research is better when there are no individual differences, therefore a strength of the repeated measures design is that the same participants are used in each condition and therefore there are no participant variables. However, when using a design like the independent measures design, participant variables are created which may lower a study’s internal validity.
(3) Demand characteristics: are when participants pick up on clues and cues in the experiment which help them to guess what the research is about and predict what the experimenter is looking for. When participants pick up on such clues and cues they often change the way they would naturally behave they act in a way that will give the experimenter what they want so that they appear ‘normal,’ or they may deliberately act in a way that is different to what the experimenter is looking for to avoid being a conformist. Again, demand characteristics are an extraneous/confounding variable that experimenters do not want in their study (remember, the experimenter is looking to observe the effects of just the IV on the DV). A weakness of the repeated measures design is that it can create demand characteristics (participants taking part in each condition can help them to guess the aim of the study). A strength of the independent measures design is that participants only take part in one condition therefore demand characteristics are minimised.
(4) Order effects: When participants repeat a task, results can be affected by order effects. Order effects include:
* Performing less well than you would normally due to boredom or fatigue
* Performance improving through practice in the first condition
A strength of the independent measures design is that because participants only take part in one condition participants are less likely to become border or practiced and therefore the experiment is more likely to measure natural real-life behaviour. On the other hand, a weakness of the repeated measures design is that because participants take part in all the conditions in the research they are more likely to become bored or practiced as they progress through the conditions which will result in measuring unnatural behaviour thus lowering internal validity.
The table below outlines the strengths and weaknesses associated with the three experimental designs.
Independent Measures | Repeated Measures | Matched Pairs |
(+) Reduces the chances of demand characteristics because participants only take part in one condition they are less likely to pick up on clues and cues in the experiment which could lead to participants changing their behaviour in order to please the experimenter. This is a strength because it means that the experiment will have high internal validity and will measure what it intends to. (+) Reduces the chances of order effects. Because participants are only tested in one condition so they will not improve through practise or become bored through repetition. This is a strength because it means that the experiment will have high internal validity and therefore is measuring what it intends to. | (+) Less participants are required because the same participants are used in all of the conditions. This means that less money is spent. (+)Participant variable are eliminated as the same participants are being used in each condition. This means that participant variables are kept consistent, providing all other EVs are controlled this means that the only variable to change across the different conditions is the IV which means that a cause and effect relationship can be established. | (+) Reduces the chances of demand characteristics because participants only take part in one condition they are less likely to pick up on clues and cues in the experiment which could lead to participants changing their behaviour in order to please the experimenter. This is a strength because it means that the experiment will have high internal validity and will measure what it intends to. (+) Reduces the chances of order effects. Because participants are only tested in one condition so they will not improve through practise or become bored through repetition. This is a strength because it means that the experiment will have high internal validity and therefore is measuring what it intends to. |
(-) Requires twice the number of participants needed by a repeated measures design which is a weakness because it could make the research more expensive to carry out. (-) High chance of participant variables as different participants are being used in each condition. This means that the IV isn’t the only variable to change across the different conditions and therefore a cause and effect relationship cannot be established. | (-) Increases the chances of order effects as participants take part in all the conditions in the research and therefore they are more likely to become bored or practiced as they progress through the conditions which will result in measuring unnatural behaviour thus lowering internal validity. (-)A weakness of the repeated measures design is that it can create demand characteristics, participants taking part in each condition can help them to guess the aim of the study and therefore change their behaviour. This is a weakness as if the participants are not acting how they would naturally, the researcher is not measuring what they intend to measure which would lead to low internal validity. | (-) Requires twice the number of participants needed by a repeated measures design which is a weakness because it could make the research more expensive to carry out. (-) High chance of participant variables as different participants are being used in each condition. This means that the IV isn’t the only variable to change across the different conditions and therefore a cause and effect relationship cannot be established. |