The Purpose and Power of Control Groups, Explained

UPI Study › Courses › Research Methods in Psychology › Free lessons › Lesson 12.3 Free with a free account

The Purpose and Power of Control Groups

Research Methods in Psychology · Chapter 12: Experimental Design FundamentalsSection 12.3 · lesson 72 of 949 min · free with a free account

← Why Random Assignment MattersNext lesson: Setting Up Two-Group Experiments →

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

Why every experimental claim needs a comparison condition.

  • Explain why control groups make results interpretable
  • Distinguish no-treatment, placebo, waitlist and active controls
  • Name the validity threats a control group addresses
  • Select an appropriate control for a given question

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 (1,265 words). Read along, or search it.

Experimental Design Fundamentals

The Purpose and Power of Control Groups

An experimental result is never a single number. It is always a comparison. This section is about the thing you compare against, the control condition. By the end you will explain why control groups are essential for interpreting results. You will distinguish among no-treatment, placebo, waitlist, and active controls. You will name the validity threats that control groups specifically address. History, maturation, testing effects, regression, and placebo effects. You will select an appropriate control condition for a given research question. And you will weigh the ethical considerations that come with withholding treatment.

The Problem

Knowing What Counts as Change

Picture a six week stress reduction program delivered to a group of participants. By the end of the study, their reported anxiety scores have dropped. Has the program worked? On its own, that data simply cannot answer the question. The drop might reflect the program. It might also reflect the passage of time. Or the seasonal lull at the end of an academic term. Or, more subtly, the comfort of being asked thoughtful questions by a researcher. Notice that all four explanations predict exactly the same result. Without a comparison group, none of them can be ruled out. A pre and post drop is not evidence of an effect. It is a description of a change.

The Fix

What a Control Group Is

A control group provides the comparison that makes the change interpretable. It is assembled the same way as the treatment group. Comparable participants, allocated by the same procedure. It is exposed to the same setting, the same procedures, and the same measurement. One thing, and only one thing, is withheld. The specific manipulation under investigation. Now the difference between the two groups at the end of the study means something. It can be attributed to the manipulation, rather than to anything else that happened. The design is deliberately boring. That is exactly the point.

The Logic

An Effect Is a Difference, Not a Change

Here is the idea that reframes how you read every results section. The effect of a manipulation is not the absolute change in the treatment group. It is the difference between what happened, and what would have happened without it. That second quantity is the awkward one. Researchers cannot observe both outcomes for the same person. You either get the treatment or you do not. Never both. So they approximate the missing alternative using the control group. A set of comparable participants who did not receive the manipulation. Which means the validity of the whole experiment rests on one thing. How well the control group represents what would have happened to the treatment group.

Threats Addressed

Five Things a Control Group Protects Against

Control groups protect against several specific threats to internal validity. Each of these would otherwise produce a misleading result. The first is history, meaning external events that occur during the study period. A news event, a policy change, an exam season. Both groups experience the same external events, so differences cannot be due to history. The second is maturation, the natural changes in participants over time. Fatigue, growth, learning. Children in particular are always changing. Maturation affects both groups equally, so only manipulation-specific change remains. The third is testing effects, improvement on a measure just from having taken it before. Both groups receive the same tests, so those testing artifacts cancel out.

Two More Threats

Regression and Expectation

Two more threats deserve their own naming. Statistical regression is the tendency of extreme scores to move toward the mean. If you select the most anxious people, some of that score was a bad day. Retest them and they drift back, whether or not you treat them. Regression operates equally in both groups when participants are similarly selected. The other threat is placebo effects. That is improvement caused by the participant's expectation of receiving help. A placebo control receives the same expectation, without the active ingredient. Both of these produce genuine improvement that has nothing to do with the treatment. Only a matched comparison group lets you subtract them out.

Control Type One

No-Treatment Control

Not every control group looks the same. The kind of comparison you need depends on the question, and on the likeliest threat. The simplest is the no-treatment control. Control participants receive nothing at all during the study period. They are measured at the same times, on the same instruments, as the treatment group. They are simply not exposed to the intervention. This isolates the effect of any treatment against the absence of treatment. But there is something it cannot do. It cannot separate the active ingredients from non-specific effects like attention or expectation. So a positive result tells you something happened. Not what.

Control Type Two

Placebo Control

A placebo control closes exactly that gap. Participants receive an inert version of the manipulation. A pill without active ingredients, for example. Or a generic conversation, in place of structured therapy. Or a sham procedure, matched in setting and time to the real one. The matching is the whole design. Same room, same duration, same attention. Comparing treatment with placebo isolates the specific effect of the active ingredient. It separates that from the general effects of simply being treated. Placebo controls are essential in clinical research. They are increasingly common in psychological intervention studies too.

Control Types Three and Four

Waitlist and Active Controls

Two further control types answer different questions again. Waitlist controls receive the intervention after the study period ends. During the study, they serve as the comparison group. Afterwards, they receive whatever benefit the treatment group already got. This design is common when the intervention is scarce or expensive. It also helps when ethical concerns make a true no-treatment control problematic. Active controls take a different approach entirely. Participants receive an alternative intervention, typically an existing standard treatment. Comparing a new therapy with an established one tests whether it offers any advantage. So the question is no longer whether the treatment works at all. It is whether the treatment works better than what is already available.

Ethics

Withholding Is a Decision With a Cost

There is an uncomfortable side to control conditions that is worth facing directly. Withholding a potentially beneficial treatment from participants raises serious ethical concerns. That is especially true in clinical contexts, where the stakes are health, not test scores. Researchers and ethics review boards have to weigh two things against each other. The scientific value of the comparison, and the cost to participants in the control condition. Neither side automatically wins. The common compromises are the designs you have just met. Waitlist designs, active controls, and partial-treatment comparisons. So the choice of control condition is not only a methodological decision. It is an ethical one, and review boards treat it that way.

Selection

Let the Question Choose the Control

Choosing a control condition begins with the research question, not with convention. Ask whether the intervention has any effect at all. That question needs a no-treatment or placebo comparison. Ask whether a new approach beats an existing one. That question needs an active comparison, against the current standard. Now ask which of two mechanisms is doing the work. Mindfulness practice versus muscle relaxation, for instance. That needs a control which isolates exactly the contrast of interest. And you are not limited to one. Several control conditions can be combined in a single experiment, answering several questions at once.

The Common Error

A Control Group Is Active, Not Absent

Finish with the mistake that undoes all of this. Treating the control condition as a passive absence, rather than an active comparison. A control group is not the people you left alone. Control participants need the same attention as treatment participants. The same setting. The same data collection. And ideally the same expectations about what is going to happen to them. Here is why that matters so much. Anything that systematically differs between conditions, other than the manipulation, becomes a confound. At that point the control group has flipped role entirely. It stops being a protection against bias, and becomes a source of one.

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 The Purpose and Power of Control Groups

Why do experiments need a control group?
Experiments need a control group because a change in the treatment group alone cannot show what caused it. A drop in anxiety after a stress-reduction program could reflect the program, the passage of time, a seasonal lull, or the attention of being studied. A comparable control group, treated identically except for the manipulation, estimates what would have happened without the treatment, so the difference between groups can be attributed to the manipulation.
What is the difference between a placebo control and a no-treatment control?
A no-treatment control group receives nothing but is measured at the same times on the same instruments, so it shows whether the treatment beats no treatment but cannot separate active ingredients from attention or expectation. A placebo control group receives an inert version matched in setting, duration, and attention, such as a pill without active ingredients or a sham procedure, which isolates the specific effect of the active ingredient.
What is a waitlist control group?
A waitlist control group serves as the comparison during the study and then receives the intervention after the study period ends. It is common when an intervention is scarce or expensive, or when withholding treatment entirely would raise ethical concerns. An active control group is a different option: participants receive an alternative, usually the existing standard treatment, which tests whether a new intervention works better than what is already available.
Which threats to internal validity does a control group protect against?
A comparable control group protects against history, maturation, testing effects, statistical regression, and placebo effects. Both groups experience the same outside events, the same natural change over time, the same repeated measurement, and, if selected the same way, the same regression toward the mean, while a placebo control also equalizes expectations. The control group must receive the same attention, setting, and data collection, or it becomes a source of bias.

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 →