Experimental Design (College Board AP® Psychology): Revision Note

Independent groups design & random assignment

• The type of experimental design used determines how participants are assigned to conditions of the IV and how data is collected and compared

• In an independent groups design, participants experience only one condition of the IV

  • This is also known as a between-subjects design

• Two separate groups of participants are used, each generating their own data set:

  • Group 1 experiences condition A of the IV

  • Group 2 experiences condition B of the IV

• The scores of participants in condition A are compared to the scores of participants in condition B, e.g.

  • Participant 1 learns a poem with music playing (condition A)

  • Participant 2 learns the same poem in silence (condition B)

  • The DV is measured as the number of words correctly recalled from the poem in 5 minutes

  • Each participant produces one score from participating in one condition only

Random assignment in independent groups design

• In an independent groups design, participants are randomly assigned to each condition of the IV

• Random assignment is the process of allocating participants to conditions by chance, so that every participant has an equal probability of being placed in either condition, e.g.

  • The name of every participant in the sample is placed into a hat

  • The researcher draws the first name and assigns this person to condition A

  • The researcher draws the second name and assigns this person to condition B

  • This continues until all participants have been assigned to a condition

  • For larger samples, random name-generator software may be used

• Random assignment is used to avoid researcher bias and to control for participant variables that could act as confounding variables

• By randomly assigning participants to conditions, the researcher reduces the likelihood that these differences will systematically favor one condition over another

Evaluation of independent groups design

Strengths

• The use of independent groups design means that demand characteristics are less likely to act as a confounding variable

  • As participants only take part in one condition of the IV, they are less likely to guess the aim of the study and alter their behavior accordingly

  • This increases the internal validity of the study

• As participants experience only one condition, it means that order effects are eliminated

  • Participants will not become tired, bored or overly practised at the task

  • This is a strength as it increases the validity of the findings

Limitations

• Participant variables may affect the validity of the findings

  • If participants with a particular characteristic are disproportionately assigned to one condition, this creates an uneven playing field

  • The results are thus not a true measure of the IV's effect on the DV

• More participants are needed compared to a repeated measures design

  • Each condition requires its own group of participants, which may cause logistical issues and could result in smaller condition sizes

  • This reduces the reliability of the findings

Repeated measures design & counterbalancing

• In a repeated measures design, participants experience all conditions of the IV — this is also known as a within-subjects design

• Each participant's score in condition A is compared to their own score in condition B

  • Participants act as their own control group — individual differences are held constant because the same person completes both conditions

• For example:

  • Participant 1 learns a poem with music playing (condition A)

  • Participant 1 then learns a different poem in silence (condition B)

  • The DV is measured as the number of words correctly recalled from the poem in 5 minutes

  • Participant 1's score in condition A is directly compared to their score in condition B

Order effects

• A repeated measures design may give rise to order effects — where the order in which participants complete the conditions affects their performance

• Order effects include:

  • fatigue — completing more than one condition may tire participants, impairing performance in the second condition

  • boredom — extended participation may cause participants to lose interest, reducing effort in later conditions

  • practice — if both conditions involve a similar task, participants may improve their performance in the second condition simply due to familiarity

Counterbalancing

• To control for order effects, researchers use counterbalancing

• This is where the researcher splits participants into two equal groups:

  • Half of the participants complete condition A first followed by condition B

  • The other half complete condition B first followed by condition A

• This ensures that any order effects are distributed evenly across both conditions rather than systematically affecting one condition more than the other

• Without counterbalancing, order effects would act as a confounding variable — they could explain differences in the DV independently of the IV

  • This would make it impossible to determine whether it was the IV or the order of conditions that caused any change in performance

Evaluation of repeated measures design

Strengths

• Participant variables are not an issue with a repeated measures design

  • This is because each participant's performance in one condition is measured against their performance in another condition

  • This controls for individual differences, increasing internal validity

• Fewer participants are needed for a repeated measures design

  • Each participant generates scores for both conditions

  • This reduces the sample size required and makes it easier to recruit sufficient participants

Limitations

• Demand characteristics may become a confounding variable

  • As participants take part in both conditions of the IV they are more likely to guess the aim of the study and alter their behavior accordingly

  • This decreases internal validity

• If not controlled for, order effects may lower the validity of the study

  • Participants may become tired, bored or overly practised at the task

  • This is a limitation as the researcher cannot be confident that changes in the DV were caused by the IV rather than the order of conditions

Matched pairs design

• In a matched pairs design, participants are paired based on a characteristic or variable that is relevant to the research

  • Each member of the pair is assigned to a different condition of the IV

• Participants may be matched on variables such as:

  • age

  • gender

  • IQ

  • personality traits (e.g. aggression levels)

• Participants may be matched on more than one variable

  • E.g. Maguire et al. (2000) matched their sample of London taxi drivers with a control group on age, gender, and handedness

• By matching participants across conditions, the researcher ensures that one condition does not include a disproportionate number of participants with a particular characteristic

  • Once matched, each member of the pair is randomly assigned to one condition

• Because each participant is paired with a counterpart, this design produces related data — one participant's score is compared to their matched partner's score

• For example:

  • In a study on the social learning of aggression, participants are matched on a pre-existing aggression scale

  • Participant 1, who scores 10 for aggression, is matched with Participant 2, who also scores 10

  • Participant 1 is assigned to condition A; Participant 2 is assigned to condition B

  • This controls for pre-existing aggression as a confounding variable — any difference in scores should be due to the IV, not natural aggression levels

• Identical (monozygotic) twins are sometimes used in matched pairs designs as they represent the ideal matched pair, sharing identical DNA and typically the same upbringing:

  • One twin is assigned to the experimental condition; the other is assigned to the control condition

Evaluation of matched pairs design

Strengths

• Individual differences are largely controlled as a confounding variable in a matched pairs design

  • The researcher has carefully matched each participant with a similar counterpart

  • This means that participant variables are controlled to a greater extent than in an independent groups design, increasing reliability

• As participants take part in only one condition of the IV this means that demand characteristics are reduced

  • This makes them less likely to guess the aim of the study, which increases the validity of the findings

Limitations

• Matching is a difficult and time-consuming process

  • It is often impossible to match the participants across all relevant criteria

  • Even well-matched participants may differ in motivation, skill, or ability, which reduces the reliability of the study

• If one participant drops out of the research, then the researcher must find a suitable replacement who matches the remaining participant

  • This is logistically challenging, can slow down the research process, and may jeopardize funding if the study is working to a timeline