Tracking Change: Longitudinal and Cross-Sectional Methods

UPI Study › Courses › Research Methods in Psychology › Free lessons › Lesson 7.3 Free with a free account

Tracking Change: Longitudinal and Cross-Sectional Methods

Research Methods in Psychology · Chapter 7: Quasi-Experimental and Time-Based DesignsSection 7.3 · lesson 42 of 9410 min · free with a free account

← Working with Ex Post Facto ResearchNext lesson: The Logic of Pretest-Posttest Designs →

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

Choosing between snapshots and movies in the study of change.

  • Distinguish cross-sectional from longitudinal designs
  • Identify trend, cohort and panel variants
  • Separate age, period and cohort effects
  • Match the design to the research 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 (1,347 words). Read along, or search it.

Quasi-Experimental and Time-Based Designs

Tracking Change: Longitudinal and Cross-Sectional Methods

How does language ability develop across childhood? Do political attitudes shift across the life-course? Does job satisfaction rise or fall as people advance in their careers? Every one of those is a question about change over time. There are two basic ways to study change, and they are not equivalent. You can take a snapshot, or you can shoot a movie. By the end of this section you will distinguish the two, and their variants. You will separate age effects from period effects and cohort effects. And you will be able to match a design to a question, which is the real skill.

Two Strategies

A Snapshot or a Movie

Cross-sectional research takes a snapshot. It measures different people at different ages or stages, at a single moment in time. Longitudinal research follows people across time, measuring them at multiple points. The difference sounds like logistics. It is actually about what you can conclude. Cross-sectional designs are quick and inexpensive. But they can confuse age effects with generational differences. Longitudinal designs trace genuine change. But they are expensive, slow, and prone to losing participants along the way. Understanding that trade-off is essential to choosing a design. It is equally essential to evaluating one that somebody else chose.

The Snapshot

What Cross-Sectional Designs Do Well

Start with the snapshot, because it is the more common of the two. Imagine interviewing two hundred people aged twenty. Then two hundred aged forty, and two hundred aged sixty. All in the same year, and you compare their attitudes toward technology. That is a cross-sectional study. One round of data collection, completed quickly, which is why they are everywhere. They reveal patterns of variation across age, generation, or other categories. How does loneliness compare across age groups today? What proportion of different demographic categories supports a given policy? They also support correlational analysis among variables measured at the same time. These are genuinely useful questions. Note that all of them are about now.

The Snapshot's Limit

The Question a Snapshot Cannot Answer

Now the limitation, and it is a deep one. Cross-sectional designs cannot directly track change. Suppose your twenty-year-olds are more comfortable with smartphones than your sixty-year-olds. Two completely different stories fit that result equally well. The first is an age story. Something about being twenty, versus being sixty. If that is right, today's twenty-year-olds will grow uncomfortable with future technologies too. The second is a cohort story. Something about growing up in a different era. If that is right, they learned a permanent comfort that will persist as they age. These predictions are opposite, and they matter enormously for policy. But the difference you observed may reflect age, cohort, or both. Cross-sectional data cannot distinguish them. And notice, a bigger sample does not help. This is a structural limit of the design.

The Movie

Three Variants of Longitudinal Research

The alternative is to actually follow people through time. Longitudinal research measures a population at two or more points. In some variants it is the very same individuals, in others different members of the same population. The payoff is that you observe change directly, instead of inferring it from a comparison. There are three main variants, and it helps to order them by resolution. A trend study resolves change at the level of the population. A cohort study resolves it at the level of a defined group. A panel study resolves it at the level of the individual person. Each step down that list buys you finer resolution. Each step also costs more money, more time, and more effort to keep people enrolled.

Populations and Generations

Trend and Cohort Studies

Take the first two variants together. A trend study surveys different samples from the same population at different times. National opinion polls repeated every year are the obvious case. So are repeated cross-sections of the General Social Survey, and census data collected every ten years. Trend studies show whether a population's attitudes or behaviors are changing. What they cannot do is follow any individual. The population can shift while every single person in it stays the same. A cohort study follows a defined group across time. The group shares some defining characteristic, such as a birth year or a graduation year. The classic case is a birth cohort. Everyone born in a given year in a particular country, followed across decades. That design illuminates generational patterns, and change between generations.

Same People, Many Waves

Panel Studies and Within-Person Change

Panel studies are the most powerful of the three. They follow the same individuals across waves of measurement. So change can be examined at the level of the individual person. That unlocks a distinction worth learning carefully. Within-person change is change in one individual's outcome, from one measurement to another. Between-person difference is a difference among different people, measured at the same time. These two often point in different directions, which surprises people. Here is the example that makes it concrete. People who become unemployed may show declining well-being. Yet the unemployed at any one moment are not, on average, less well than the employed across all of life. Both statements can be true at once. Only panel data can answer the first question, and aggregated data cannot. That is why panel studies are among the most informative, and the most demanding, designs we have.

Three Effects

Age, Period, and Cohort

Three kinds of effect co-exist in any study of change. Telling them apart is one of the central methodological challenges of this work. An age effect is change associated with growing older. It happens regardless of when you were born or what is going on in the world. Memory speed declining after about age sixty is an age effect. A period effect is change associated with the historical moment. It hits all age groups simultaneously. The widespread decline in mental health during the pandemic of twenty twenty is a period effect. A cohort effect is change associated with the generation in which you grew up. Generation Z grew up with smartphones in a way earlier generations did not. Read those three definitions again and notice how easily they blur together. In real data they almost always co-occur.

A Hard Confound

Why the Three Cannot Simply Be Separated

Now the part that makes this genuinely hard. Age, period, and cohort are mathematically confounded. Any one of the three can be computed from the other two. Know someone's birth year and the current year, and you know their age. Know their age and the current year, and you know their birth year. So the three are not merely correlated in practice. They are locked together by arithmetic. No amount of extra data breaks that identity on its own. Disentangling them takes sophisticated statistical methods. It also takes combining cross-sectional and longitudinal data. The strongest evidence comes from cohort-sequential designs, also called accelerated longitudinal designs. These combine longitudinal follow-up with multiple birth cohorts. You watch several generations age at once, and the patterns begin to separate.

The Trade-Off

Comparing the Two Approaches

Line the two approaches up on the criteria that decide real projects. Cost. Low for cross-sectional, high for longitudinal. Time to results. Quick versus slow, often measured in years. Tracking individual change. Cross-sectional cannot, a panel design can. Distinguishing age from cohort effects. Cross-sectional does it poorly, longitudinal does it better. Note the word better, rather than perfectly. Vulnerability to attrition. Cross-sectional has none, longitudinal always does. Causal inference. Weak from a snapshot, stronger from a longitudinal design, but only with care. On one criterion the snapshot wins outright. For a population-level picture it is strong, while longitudinal work manages it only through the trend variant.

Choosing Well

Match the Design to the Question

So which design is better? That is the wrong question. There is no universally superior design. The research question decides. How common is this in the population today? That is a cross-sectional question. How does this develop over the life-course? That is a longitudinal question. Questions about generational or historical change call for trend or cohort approaches. One more term to carry with you, because it is the recurring cost of longitudinal work. Attrition is the progressive loss of participants from a study over time. It biases results, because the people who stay differ from the people who leave. Here is the failure mode to watch for in published work. Researchers who answer longitudinal questions with cross-sectional data produce inferences the data cannot support. And it works the other way around just as badly.

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 Tracking Change: Longitudinal and Cross-Sectional Methods

What is the difference between cross-sectional and longitudinal research?
Cross-sectional research measures different people at different ages or stages at one point in time, while longitudinal research measures a population at two or more points in time. Cross-sectional studies are quick and inexpensive and show differences across groups now. Longitudinal studies observe change directly but are slower, more expensive, and vulnerable to attrition, the progressive loss of participants over time.
What are age, period, and cohort effects?
An age effect is change tied to growing older, regardless of birth year or historical events. A period effect is change tied to a historical moment that affects all age groups at once, such as the widespread decline in mental health during the 2020 pandemic. A cohort effect reflects the generation someone grew up in, such as Generation Z growing up with smartphones in a way earlier generations did not.
Why can't a cross-sectional study separate age effects from cohort effects?
In a cross-sectional study, people of different ages also belong to different generations, so any age difference may reflect aging, upbringing, or both. If twenty-year-olds are more comfortable with smartphones than sixty-year-olds, the cause could be age or growing up in a different era. A larger sample does not help. Cohort-sequential, or accelerated longitudinal, designs follow several birth cohorts over time to help separate the two.
What is the difference between within-person change and between-person differences?
Within-person change is change in one individual's outcome from one measurement to the next, while a between-person difference compares different people measured at the same time. The two can point in different directions, so a pattern found across people does not automatically describe how each individual changes. Panel studies, which measure the same individuals repeatedly, are needed to examine within-person change directly.

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 →