- Psychology: research methods and statistics
What are the types of experimental design in psychology?
There are three main types of experimental design in psychology. In independent groups each participant takes part in one condition only; in repeated measures every participant does every condition; in matched pairs participants are paired on a relevant trait and each member of a pair goes to a different condition. Each design trades one problem for another, and counterbalancing handles the order effects of repeated measures.
The topic explained
Three ways to share out the conditions
An experiment compares conditions, for example studying a word list with music and studying it in silence. The experimental design is the plan that says which participants do which condition, and psychology uses three main types. In independent groups, also called a between-subjects design, each person does only one condition: twenty students learn with music, twenty others in silence, and the groups' scores are compared.
In repeated measures, a within-subjects design, the same people do every condition: each student learns one list with music and another in silence, and their own two scores are compared. In matched pairs, the researcher first measures a trait that could affect the result, say a memory pretest, pairs people with similar scores, and sends one member of each pair to each condition.
What each design costs
Independent groups avoid any carry-over between conditions, but the groups are different people. If the music group happens to include better memorizers, the difference in scores comes from participant variables, the ways people differ, and not from the music. Random allocation reduces this risk, and it works better with more participants, so the design needs a larger sample.
Repeated measures remove participant variables, because each person is compared with themselves, and they need half the people. Their price is order effects: in the second condition a participant may do better from practice or worse from tiredness and boredom, and having seen both conditions, may guess the aim. Matched pairs keep the people separate while controlling the matched trait, but matching takes time, it controls only what was measured, and if one member drops out the pair is lost. The common mistake is to call repeated measures the best design without a cost; a good answer names a weakness of the design chosen and how to reduce it.
Counterbalancing: a real example from 1935
The usual fix for order effects is counterbalancing: half the participants do condition A first and then B, and the other half do B first and then A. Practice and tiredness still happen, but they now fall equally on both conditions, so they cannot create a difference between them.
J. Ridley Stroop used exactly this in his 1935 study of interference. In his second experiment 100 students did two tasks: naming the colors of printed squares, and naming the ink color of color words printed in a different color, such as the word red printed in green. Every student did both, a repeated measures design, and half did the tasks in the order squares, words, words, squares, the other half in the reverse order, to equate practice and fatigue. Naming 100 colors took 63.3 seconds on average with the squares and 110.3 seconds with the conflicting words, 47 seconds or about 74 percent longer.
Choosing a design for a question
The choice follows from the question. If doing one condition would change how a person does the other, for example learning the same story twice, or a teaching method that cannot be unlearned, use independent groups or matched pairs. If people differ a lot on the task and participants are few, repeated measures with counterbalancing give a fairer comparison. Stroop's design worked because the effect was large and each task took only minutes.
Practice: types of experimental design
For 10th grade psychology students. Answer each question from the page, then check your work against the answers.
Free, no sign-up. The answer key prints on the second page. Regenerating a new worksheet on the same topic needs a free account.
Name the three types of experimental design and say in one sentence what each participant does in each.
Write the main weakness of each design.
Complete the plan: what does group 2 do, and in what order?
Read the chart. How many seconds longer did the conflicting words take, and by about what percent?
Why did Stroop give half his students the order squares, words, words, squares and the other half the reverse?
A researcher tests a new reading method on 30 pairs of children using matched pairs. Suggest one trait to match on and explain why.
A student tests whether coffee improves reaction time: the same ten friends are tested without coffee at 8:00 and with coffee at 8:30. Evaluate the design and suggest an improvement.
Common questions
Which experimental design is the best?
No design is best for every question. Repeated measures control differences between people but suffer from order effects; independent groups avoid order effects but need more people; matched pairs sit in between. The right choice depends on whether one condition would change performance in the other.
What is the difference between order effects and demand characteristics?
Order effects come from the sequence itself: practice, tiredness or boredom change performance in the later condition. Demand characteristics are cues that let participants guess the aim and change their behavior, which repeated measures make more likely because people see every condition.
Is matched pairs the same as repeated measures?
No. In matched pairs different people do each condition, but they are paired on a trait such as age or a pretest score. Only in repeated measures does the same person do every condition.
Can counterbalancing remove order effects completely?
It does not stop practice or fatigue, but it spreads them equally across the conditions so they cannot favor one. If one order changes people differently from the other, a carry-over effect, counterbalancing is not enough and independent groups are safer.
What do between-subjects and within-subjects mean?
They are other names for the designs. Between-subjects compares different people, as in independent groups. Within-subjects compares each person with themselves across conditions, as in repeated measures.

Still have a question? Ask Lessi
Any question about this subject. Lessi answers right here, step by step.
Try asking
Asking needs a free account; your question is kept while you sign up. Answers are written by AI and can contain mistakes. Lessi doesn’t give medical or legal advice.
Learn it with a teacher
Learn this topic live with Lessi
Lessi, the AI teacher, explains it out loud on a board, with short quizzes, at your pace. The first 60 minutes are free.