Experimental designs

Independent groups

• When two separate groups of participants experience two different conditions of the experiment. If there are two levels of the IV this means that all participants experience one level of the IV only. The performance of the two groups would then be compared

• For example, one group of participants (group 1) drink an energy drink (condition A, the experimental condition) A different group of participants (group 2) drink water (condition B, the control condition)

Repeated measures

• All participants take part in all conditions of the experiment. Following this, the two mean scores from both conditions would be compared to see if there was a difference

• For example, each participant would first experience condition A (the experimental condition) Each participant would then later be tested again in condition B (the control condition)

Matched pairs design

• Participants are grouped together on a variable or variables relevant to the experiment. For instance, in a memory study participants might be grouped on their IQ, as this might be a good indicator of their ability to recall information. One member of the pair is assigned to condition A and the other to condition B

• This is an attempt to control for the confounding variable of participant variables and often requires the use of a pre-test if it is to be effective

Evaluation of independent groups: Weaknesses

• Participants who occupy the different groups are not the same in terms of participant variables. If a researcher finds a mean difference between the groups on the DV, this may be more to do with participant variables than the effects of the IV. Such differences act as a confounding variable, reducing the validity of findings. To deal with this problem researchers use random allocation

Random allocation

• Addressing the problem of participant variables in an independent groups design. Participants go through this to the different experimental conditions. It attempts to evenly distribute across conditions of the experiment

Random allocation example

• Pieces of paper with A or B written on them are placed in a hat and the researcher selects them one at a time to assign participants to groups

Evaluation of independent groups: Weaknesses

• Less economical than repeated measures as each participant contributes a single result only. Twice as many participants would be needed to produce equivalent data to that collected in a repeated measures design. This increases time/money spent on recruiting participants

Evaluation of independent groups: Strengths

• Order effects are not a problem whereas they are a problem for repeated measures design. Participants also less likely to guess the aims of the study

Evaluation of repeated measures: Weaknesses

• Each participant has to do at least two tasks and the order of these tasks may be significant (there are order effects). To deal with this, researchers use counterbalancing. Could also arise because repeating two tasks could create boredom or fatigue, causing performance to worsen on the second task. Performance may also improve through the effects of practice, especially on a skill-based task, meaning they perform better on the second task

• Order acts as a confounding variable

Evaluation of repeated measures: Weaknesses

• It is more likely the participants will work out the aim of the study when they experience all conditions of the experiment. For this reason, demand characteristics tend to be more of a feature of repeated measures design than independent groups

Evaluation of repeated measures: Strengths

• Participant variables are controlled (therefore higher validity) and fewer participants are needed (therefore less time/money spent recruiting them)

Counterbalancing

• An attempt to control order effects in a repeated measures design. In this, half the participants take part in condition A then B, and the other half take part in condition B then A. Does not remove or prevent the problem, but attempts to balance out the effects

• ABBA technique, i.e. every participant does four trials, A, B, B, then A

Counterbalancing example

• Participant 1: A-B Participant 2: B-A Participant 3: A-B and so on

Evaluation of matched pairs: Strengths

• Participants only take part in a single condition so order effects and demand characteristics are less of a problem

Evaluation of matched pairs: Weaknesses

• Although there is some attempt to reduce participant variables in this design, participants can never be matched exactly. Even when identical twins are used as matched pairs, there will still be important differences between them that may affect the DV

Evaluation of matched pairs: Weaknesses

• Matching may be time-consuming and expensive, particularly if a pre-test is required, so this is less economical than other designs