Working with Within-Subject Designs, Explained

UPI Study › Courses › Research Methods in Psychology › Free lessons › Lesson 13.5 Free with a free account

Working with Within-Subject Designs

Research Methods in Psychology · Chapter 13: Factorial, Within-Subject, and Small-n DesignsSection 13.5 · lesson 81 of 949 min · free with a free account

← Applying Multivariate Experimental DesignsNext lesson: Strategies for Managing Carryover Effects →

Earn 3 college credits for Research Methods in PsychologyRecommended for credit by NCCRS · Psychology 111 · self-paced · one payment, lifetime access
Enroll in Research Methods in Psychology · $250 →Download the syllabus (PDF)

In this lesson

Each participant as their own control, and what that buys.

  • Describe the structure of a within-subject design
  • Explain why its statistical power is higher
  • Recognize order effects, fatigue and demand characteristics
  • Judge when the architecture is and is not appropriate

Free study notes

Get this lesson's notes by email

The key points and 4 practice questions with answers, in your inbox. One email, free.

One email. Unsubscribe in one click.

Transcript

Everything said in the video, section by section (1,180 words). Read along, or search it.

Factorial, Within-Subject, and Small-n Designs

Working with Within-Subject Designs

Here is an idea that sounds almost too good to be true. Instead of comparing two groups of people, compare each person to themselves. That is the within-subject design, and it is genuinely powerful. By the end of this section you will describe its structure. And explain how it differs from a between-subject design. You will identify its statistical and practical advantages. You will recognize the threats specific to it, including order effects, fatigue, and demand characteristics. You will apply the design appropriately, given the nature of the manipulation. And you will evaluate published within-subject studies for design quality.

The Logic

Compare Within the Person

A within-subject design exposes every participant to every condition. It then compares outcomes within each person, rather than between groups of different people. The same individual provides data under treatment and under control. So the comparison rests on differences observed in the same brain. The same body, and the same personal history. Now think about what that removes from the comparison, automatically. Personality. Intelligence. Mood on the day. Prior experience. Every one of those plagues between-subject designs, and none of them can differ here. Each participant is, in effect, their own control. That single sentence is the whole appeal of the architecture.

Structure

A to B, and Onward

The simplest within-subject design has two conditions, usually called A and B. A participant performs the task under condition A. Then the same participant performs it under condition B. The difference between those two scores is the within-subject effect. One number per person, rather than one number per group. With more conditions, the structure just expands. A, B, C, and so on, each participant contributing one observation to every condition. And one detail is doing quiet work in the background. Order is randomized or counterbalanced across participants. That complication is taken up in detail in the next section.

Power

Why the Test Is More Sensitive

Within-subject designs are typically more powerful than between-subject designs. More powerful at the same total sample size, and often dramatically so. The reason is statistical, and worth working through slowly. When the same participant is measured in every condition, individual differences change role. They contribute only through within-person change, not through between-person variation. That matters because of what the manipulation gets tested against. The error term is the variability of the within-person differences. And that is usually much smaller than the variability of the raw scores. So the same effect stands against a much quieter background. Effects that would be invisible in a between-subjects design become detectable.

Side by Side

Where Each Source of Variability Goes

Compare where each source of variability ends up in the two architectures. Individual differences in baseline level are the big one. Between subjects, they contribute to error variance. Within subjects, they are removed from the comparison automatically. Random measurement error is the honest exception. It affects each comparison in both designs, and no architecture escapes it. Individual differences in responsiveness are handled differently again. Between subjects they add to within-condition variance. Within subjects they are captured as the within-person difference itself. And time-varying state factors are the row to watch. Between subjects, random assignment distributes them across groups for free. Within subjects, they need explicit management through counterbalancing.

Threat One

Order Effects

That last row is a warning about the rest of this section. The advantages come with vulnerabilities that between-subject designs do not share. The first is order effects. When participants experience conditions in sequence, the order itself can influence outcomes. A participant who tackles a hard task first may be tired when they reach an easy one. A participant who learns the rules in one condition may apply them in a later one. Here is why that is a threat rather than a nuisance. Differences between conditions could reflect the order rather than the manipulation. The comparison you report is no longer the comparison you designed.

Threat Two

Fatigue and Practice

The second threat is a pair of opposing forces. Fatigue tends to lower performance over the course of a session. Practice tends to raise it. Both produce systematic shifts in the dependent variable. And neither has anything to do with your manipulation. There are partial remedies. Short studies and well-spaced trials reduce fatigue considerably. But practice is harder to design away. Studies that involve novel or difficult tasks accumulate practice effects regardless.

Threat Three

Demand Characteristics

The third threat comes from the participant's own reasoning. Within-subject participants often realize that the manipulation has changed. They realize it because they experience the change directly. Consider a participant told to imagine a happy memory. Then told to imagine a sad one. They notice the contrast, and may respond strategically rather than naturally. The term for this is a demand characteristic. It is a cue in the setting that lets participants guess the purpose, and respond accordingly. Demand characteristics affect within-subject designs more than between-subject designs. The reason is simply that the contrast is immediately visible to the participant.

The Root Cause

Within-Subject Manipulations Are Transparent

That last point rests on a structural difference worth stating on its own. A between-subject design hides the manipulation from the participant. They experience only their own condition. They have no direct knowledge of the others, or even that others exist. A within-subject design reveals the manipulation by definition. The participant experiences every condition, so the design is transparent to them. And that transparency has consequences you have to plan for. It makes within-subject designs particularly vulnerable to demand characteristics. Cover stories, distractor tasks, and careful framing all matter more here. More than they do in between-subject work, where the participant sees less.

Good Fit

When Within-Subject Designs Work Best

So when should you choose this architecture? Within-subject designs suit questions where conditions can be run in one session. And crucially, without lasting effects that persist into the next condition. Perception research fits that description well. So does attention research. So does memory for stimuli that can be repeated without spoiling. More generally, task-based phenomena tend to fit. Present a stimulus, record a response, present another stimulus. Nothing about the first trial makes the second trial impossible.

Bad Fit

When to Choose Something Else

The poor fits are just as clear, and worth committing to memory. First, learned material that cannot be unlearned. Once a participant knows something, there is no returning them to ignorance. Second, treatments that produce lasting changes. The second condition is measured on a person the first condition already altered. Third, constructs that are altered by the act of measurement. Asking the question changes the answer you get next time. The choice between architectures should be made on the basis of these features. Not on convenience, and not on the convention of your subfield.

The Warning

Power Without Careful Design Is a Hazard

Let me end with a caution that runs against the obvious reading. Within-subject designs offer the highest statistical power available in experimental research. They use participants efficiently, and for many questions they are simply the right choice. That power is real. Here is what it does not mean. Power without careful design is a hazard, not a benefit. It makes order effects, fatigue, and demand characteristics more consequential. Not less consequential. More. A sensitive design registers the artifacts as readily as it registers the effect. The analysis matches the structure, using repeated-measures methods. Those exploit the pairing of observations within each participant. And the next section examines the specific procedures for controlling these threats.

About Research Methods in Psychology at UPI Study

Research Methods in Psychology (Psychology 111) is a self-paced online course of 94 video lessons in 16 chapters, from the scientific method and research ethics to designs, data collection, sampling, measurement, validity, experiments, descriptive statistics and hypothesis testing. It carries a NCCRS credit recommendation for 3 semester credits.

Every lesson transcript is free on pages like this one, and the videos are free with a free UPI Study account. Enrolling adds a practice quiz after each lesson, the graded work and final exam that earn the credit, lifetime access, and an official transcript on completion. UPI Study has helped over 130,000 students with college credits. ACE and NCCRS have over 2,100 cooperating colleges that will consider accepting credits; the final decision is with the universities.

Enroll now → Course details Download the syllabus All Psychology and social science courses Every course with PRO →

Compare: Research Methods vs Statistics

Why take it here

Why students take Research Methods in Psychology with UPI Study

How psychologists know what they knowResearch Methods in Psychology teaches how psychological studies are designed, run and judged: research ethics, surveys and observation, correlational and experimental designs, sampling, reliability and validity, and the statistics used to test hypotheses. It is a core course in psychology and many social-science degrees.
Credit at a fraction of the priceThe same 3 credits can cost $750 or more at a US college. Here it is one payment, self-paced, with lifetime access.
Finish your degree soonerTransfer credits reduce the courses you still owe, so you can graduate earlier or lighten a heavy semester.
Strengthen an applicationA completed college-level course on an official transcript shows admissions and scholarship committees you can do the work.
Study on your own scheduleNo start dates, no deadlines. Watch the lessons, practice, and take the final when you are ready.
130,000+students helped with college creditsACE and NCCRS have over 2,100 cooperating colleges that will consider accepting credits; the final decision is with the universities.

Where the credit goes

Universities that work with NCCRS

Research Methods in Psychology carries a NCCRS credit recommendation. These universities work with NCCRS; some are UPI Study's signed partners. ACE and NCCRS have over 2,100 cooperating colleges that will consider accepting credits; the final decision is with the universities.

Thomas Edison State UniversityThomas Edison State UniversitySigned partnerUniversity of the PeopleUniversity of the PeopleSigned partnerCharter Oak State CollegeCharter Oak State CollegeSigned partnerStrayer UniversityStrayer UniversitySigned partnerColumbia Southern UniversityColumbia Southern UniversitySigned partnerIndiana TechIndiana TechSigned partnerPenn StatePenn StateWorks with NCCRSSouthern New Hampshire UniversitySouthern New Hampshire UniversityWorks with NCCRSSUNYSUNYWorks with NCCRS +many more cooperating universitiesFind my college →

Find my college → Not listed? Ask Athena in the corner of this page, or book a 15-minute call.

FAQ

Questions students ask us

About Working with Within-Subject Designs

What is a within-subjects design?
A within-subjects design exposes every participant to every condition and compares outcomes within each person instead of between different groups. In the simplest version, each participant performs a task under condition A and under condition B, and the difference between the two scores is the effect. Because each person serves as their own control, stable traits such as personality, intelligence, and prior experience cannot differ between conditions.
Why are within-subjects designs more powerful than between-subjects designs?
Within-subjects designs are usually more powerful because individual differences in baseline level are removed from the comparison. The error term becomes the variability of within-person differences, which is typically much smaller than the variability of raw scores across different people. The same effect is tested against a quieter background, so effects that a between-subjects design of the same total size would miss can become detectable.
What are the main threats in within-subjects designs?
The main threats are order effects, fatigue and practice effects, and demand characteristics. Order effects occur when the sequence of conditions, not the manipulation, drives the differences. Fatigue tends to lower performance over a session while practice tends to raise it. Because participants experience every condition, they can notice the manipulation, such as recalling a happy and then a sad memory, and respond strategically. Counterbalancing, short sessions, and cover stories help manage these risks.
When should you not use a within-subjects design?
Avoid a within-subjects design when one condition leaves lasting effects on the next. Poor fits include learned material that cannot be unlearned, treatments that produce lasting change, and constructs altered by the act of measuring them. Good fits are task-based questions in perception, attention, and memory for repeatable stimuli, where conditions can run in one session without spoiling later ones. The choice should rest on these features, not on convenience.

About the Research Methods in Psychology course

How many college credits is Research Methods in Psychology?
Research Methods in Psychology (Psychology 111) carries a NCCRS credit recommendation for 3 semester credits. ACE and NCCRS have over 2,100 cooperating colleges that will consider accepting credits; the final decision is with the universities.
How much does Research Methods in Psychology cost and what is included?
$250, paid once, with lifetime access: all 94 video lessons, a practice quiz after each, the graded work and final exam, and an official transcript when you finish. Students who want several courses choose UPI Study PRO instead.
Which universities accept UPI Study credits?
UPI Study has signed partner agreements with universities such as Thomas Edison State University, University of the People and Charter Oak State College, and works with universities such as Penn State, SNHU and SUNY. ACE and NCCRS have over 2,100 cooperating colleges that will consider accepting credits; the final decision is with the universities. Use "Find my college" on this page to check yours.
How long does Research Methods in Psychology take?
It is self-paced with no deadlines. The 94 lessons total about 16 hours of video; most students add reading and practice time and finish in a few weeks to a few months, on their own schedule.
How are the exams done?
Quizzes and assignments are online in the course. The final exam is taken online with proctoring; a person on the UPI Study team checks assignments, usually within two days.
How do my credits reach my college?
When the course shows 100% complete, request the official transcript from your dashboard. It is sent to the college you name, and you can send it to more than one. Check your college first with "Find my college" on this page, or ask Athena.

Ready for the full course? Earn 3 credits in Research Methods in Psychology.

94 video lessons, a quiz after each one, and the graded work that earns the credit. Recommended for credit by NCCRS.

Enroll in Research Methods in Psychology →Download the syllabusEvery course with PRO →
Research Methods in Psychology
3 credits · NCCRSEnroll →