Experimental Designs

Experimental Designs

The experimental design specifies how participants are allocated to the conditions of an experiment — how the independent variable (IV) is administered across individuals. The three main experimental designs in psychology are repeated measures, independent groups, and matched pairs. Each has distinctive advantages and limitations relating to participant variables, order effects, and practical feasibility.

Repeated Measures Design

In a repeated measures design (also called a within-participants design), every participant takes part in all conditions of the experiment — they are measured under each level of the IV.

Strengths: eliminates individual differences (participant variables) as a confounding factor — the same person is compared across conditions, so differences in ability, personality, or background do not distort the comparison. Requires fewer participants than independent groups for the same statistical power — economical in both time and recruitment cost.

Weaknesses: susceptible to order effects — performance in later conditions may be affected by practice (improvement due to familiarity with the task) or fatigue (deterioration due to tiredness or boredom from having already completed one condition). Order effects can be controlled by counterbalancing — half the participants do Condition A first, half do Condition B first. Demand characteristics may be more pronounced — participants who complete both conditions are more likely to guess the study's purpose.

Independent Groups Design

In an independent groups design (also called a between-participants design), different participants are allocated to each condition — each person takes part in only one level of the IV.

Strengths: no order effects — each participant is only tested once, so practice and fatigue cannot carry over between conditions. Demand characteristics are reduced — participants experience only one condition and are less likely to detect the experimental manipulation.

Weaknesses: individual differences are a major potential confound — the groups may differ on participant variables (ability, age, personality) even before the IV is applied. Requires more participants than repeated measures for the same statistical power. Controlled by random allocation — randomly assigning participants to conditions distributes individual differences evenly across groups.

Matched Pairs Design

In a matched pairs design, participants are paired with another participant who is similar on key variables (e.g. IQ, age, sex), and one member of each pair is assigned to each condition. This design combines some advantages of both repeated measures and independent groups.

Strengths: controls individual differences better than independent groups (matched pairs are equivalent on the matched variables); no order effects (each participant does only one condition). Weaknesses: difficult and time-consuming to implement — matching requires measurement of participant characteristics before allocation; pairs can never be perfectly matched on all relevant variables; if one member of a pair drops out, both must be excluded.