Internal Threats: Selection, Maturation, and Their Combined Effects

UPI Study › Courses › Research Methods in Psychology › Free lessons › Lesson 10.6 Free with a free account

Internal Threats: Selection, Maturation, and Their Combined Effects

Research Methods in Psychology · Chapter 10: Internal Validity and Its ThreatsSection 10.6 · lesson 63 of 9411 min · free with a free account

← Internal Threats: History, Instrumentation, Mortality, Regression, and TestingNext lesson: Techniques for Controlling Extraneous Variables →

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 pre-existing differences and the passage of time are the hardest threats to neutralize.

  • Define selection and the designs it most damages
  • Distinguish maturation from history and from learning
  • Recognize selection-by-maturation and other interactions
  • Apply random assignment, matching and longitudinal controls

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 (1,392 words). Read along, or search it.

Internal Validity and Its Threats

Selection, Maturation, and Their Combined Effects

Two threats were held back from the previous section, and for a reason. Selection and maturation are the hardest of the classical threats to neutralize. Partly because they hide, and partly because they combine. You will define selection, and see which designs it damages most. You will distinguish maturation from history, and from genuine learning. You will meet the interactions between threats, which are where real studies fail. And you will finish with a diagnostic routine you can run on any published paper. That routine is the practical payoff of the whole chapter.

The Remainder

The Two Threats Set Aside

The previous section examined five threats with relatively clean definitions. History, instrumentation, mortality, regression, and testing. Each has a recognizable signature, and a fairly standard defense. Two further threats are at least as common, and considerably subtler. Selection, and maturation. They were held back for a specific reason. They are at their most dangerous when they interact. With each other, and with the threats already introduced. And those multi-threat patterns are what complicate real-world studies.

Threat Six

Selection, and Its Three Patterns

The selection threat refers to systematic differences between the groups compared. Differences that exist before the manipulation is ever introduced. It is the threat most often responsible for spurious causal claims in social research. Nearly every comparison across naturally occurring groups risks selection effects. Smokers versus non-smokers. Graduates versus non-graduates. Program participants versus non-participants. Selection arises whenever assignment to condition is non-random, in three common patterns. Self-selection, where participants choose their own condition. Based on personal characteristics that may also affect the outcome. Administrative selection, where an institution assigns them. Based on need, eligibility, or simple convenience. And incidental selection, where conditions come from different sources unnoticed. Treatment participants from one university, control participants from another.

Threat Six

Why Selection Is the Hardest Threat to See

Selection is the hardest threat to see, and the reason is worth dwelling on. The variables responsible may be unmeasured, unmentioned, or entirely unsuspected. A researcher who knows the treatment group is slightly older can adjust statistically. That is a solved problem. But a researcher who does not know the groups differ in conscientiousness cannot. Nor in family income, nor in prior exposure to the topic. You cannot correct for a difference you never noticed. Which is exactly why random assignment is so prized. It equalizes groups in expectation on every variable simultaneously. Including all the variables the researcher has never thought of. No amount of statistical adjustment can make that claim.

Threat Seven

Maturation

Maturation is the seventh classical threat. It refers to changes within participants that occur with the passage of time. Independent of any treatment at all. Children grow more cognitively sophisticated. Adults grow tired over the course of a session. Patients with self-limiting conditions improve because the condition runs its course. And novices develop skill through ordinary practice unrelated to any intervention. Each of those can produce pre-test to post-test differences that look like treatment effects. It differs from history in being internal. It happens inside the participant. History happens outside them, in the world. And it differs from learning produced by your manipulation in a simple way. Maturation would have occurred whether or not the manipulation was delivered.

Threat Seven

Maturation Operates on Every Time Scale

Maturation operates on every time scale relevant to research. Within a single session, fatigue and hunger and cognitive load all change. That is maturation, even though nobody grew up during your hour. Across weeks and months, mood states shift. Physical conditions resolve, and habits adjust. Across years, developmental change and biological aging accumulate. One rule follows from that range, and it is easy to apply. The longer the gap between pre-test and post-test, the more maturation can occur. And so the more important a comparison group becomes. Because only a comparison group can separate maturation from your effect of interest.

Interaction One

Selection by Maturation

Real studies are rarely threatened by one mechanism in isolation. And they can produce patterns mimicking a treatment effect. Even when no single threat would have been sufficient on its own. The most common interaction combines selection and maturation. Suppose a team compares an enrichment program for gifted students with the regular curriculum. And suppose, generously, that the two groups start at the same achievement level. So baseline selection appears to have been handled. But the gifted students may simply grow faster than average. For reasons entirely unrelated to the program. The apparent advantage of enrichment then reflects the rate of maturation. Rather than anything the program actually did. Similar interactions arise whenever groups differ in growth rate or recovery rate. Compare treatment-seeking patients against a community sample, and you have the same problem.

Interactions Two and Three

Selection by History, Selection by Instrumentation

Selection can also combine with history. Suppose your treatment group and control group are drawn from different regions. They may be exposed to different outside events between your measurements. A media campaign about the topic. A local economic shock. A regional policy change. The result looks like a treatment effect, and it reflects differential history. Selection can also combine with instrumentation, and this one is uncomfortable. Imagine measurement conducted by different staff in different conditions. The program's own staff measure outcomes in the treatment group. A research assistant measures outcomes in the control group. Raters personally invested in the program may judge ambiguous responses more favorably. Nobody has to be dishonest for that to happen. Blinding the raters to condition is the standard remedy.

The Whole Landscape

When Several Threats Point the Same Way

Step back and organize the whole landscape by source. Participant threats. Selection, maturation, and mortality. Procedural threats. Testing and instrumentation. Contextual threats. History, and the setting effects from earlier in the chapter. Statistical threats. Regression to the mean. Researcher threats. Experimenter bias and demand characteristics. And confounds proper. Extraneous variables tied to the independent variable. Real studies often involve threats from several branches at once. It is not the study where one threat clearly dominates. Those get noticed, and usually get addressed. It is the study where several modest threats all point in the same direction. Mild selection bias, modest differential attrition, a little regression, slight instrument drift. No single one would produce the observed effect. Together, they might.

Defense One

Random Assignment

These defenses are structural rather than procedural. They require choices about how participants enter the study, and which groups are compared. Random assignment is the single most powerful defense against selection. You use a chance procedure to allocate each participant to a condition. And that guarantees something specific. Any difference between groups at baseline reflects sampling variability. Rather than systematic selection of any kind. With sufficient sample size, the groups will be approximately equivalent on everything. Both the variables you measured and the ones you did not. But be precise about the claim, because it is often overstated. Random assignment does not always succeed in small samples. Chance imbalances occur. What it removes is any expected systematic difference. And it makes whatever residual differences remain statistically tractable.

Defenses Two and Three

When Randomization Is Not Available

When random assignment is impossible, two substitutes are available. Matching pairs each treatment participant with a similar control participant. Similar in age, sex, baseline score, or other relevant characteristics. Statistical adjustment pursues the same logic at the analysis stage. Through analysis of covariance, regression controls, or propensity-score methods. Both are genuinely valuable, and both share one hard limitation. They protect only against selection bias on observed variables. Matching reduces bias only on the variables you actually used for matching. The defense against maturation is different, and simple in principle. Include a comparison group experiencing the same passage of time without the manipulation. But the catch should now be obvious. The two groups must mature at the same rate. Which brings us right back to the selection-by-maturation interaction. So the strongest designs combine both. Random assignment, plus a control group of equal duration.

A Routine

Eight Questions to Ask of Any Study

Finish with a diagnostic routine you can run on any study description. Could outside events explain the result? That is history. Did the measurement procedure or the raters change? That is instrumentation. Did differential drop-out leave non-equivalent groups? That is mortality. Were participants selected for extreme initial scores? That is regression. Did the pre-test itself influence post-test responses? That is testing. Did the groups differ before the manipulation? That is selection. Could ordinary developmental or temporal change explain it? That is maturation. And finally, could two of these interact to produce the pattern you see? Assess the threats as a system, not only one at a time. Ask whether the residual threats accumulate in the same direction as the predicted effect. Working systematically through this list catches most weaknesses in published research.

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 Internal Threats: Selection, Maturation, and Their Combined Effects

What is the selection threat to internal validity?
The selection threat refers to systematic differences between comparison groups that exist before any manipulation. It arises whenever assignment is not random: through self-selection, where participants choose their condition; administrative selection, where an institution assigns people by need, eligibility, or convenience; or incidental selection, where groups come from different sources, such as two universities. It is the threat most often behind spurious causal claims about naturally occurring groups.
What is maturation as a threat to internal validity?
Maturation is change within participants that happens with the passage of time, independent of any treatment. Children develop cognitively, adults tire during a session, and people with self-limiting conditions recover as the condition runs its course. Maturation differs from history, which is an outside event, and from learning caused by the manipulation, because maturation would have happened anyway. A comparison group tracked over the same interval separates it from the treatment effect.
What is a selection-maturation interaction?
A selection-maturation interaction occurs when comparison groups change at different natural rates, so the difference in growth looks like a treatment effect. Suppose a gifted enrichment program is compared with the regular curriculum and both groups start at the same achievement level. If gifted students simply grow faster, the program will look effective even if it did nothing. Selection can also interact with history or with instrumentation, such as different raters in each condition.
How do you check a study for threats to internal validity?
Work through the classic threats one at a time. Could outside events explain the result (history)? Did instruments or raters change (instrumentation)? Did dropout differ between groups (mortality)? Were participants chosen for extreme scores (regression)? Did the pretest affect the posttest (testing)? Did groups differ beforehand (selection)? Could natural change over time explain it (maturation)? Finally, ask whether several modest threats could combine in the direction of the predicted effect.

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 →