Skip to content
Tutorials Center
My learning

Topics

Lesson 42 of 44 ยท Projects and Practice

Glossary of Research Methods in Psychology

A glossary of 40 core research methods terms in psychology, from alpha and confound to validity and WEIRD samples, with one-line definitions and a searchable tool.

Research methods has a vocabulary that sounds intimidating and is mostly common sense in disguise. This glossary gathers the terms used across the course in alphabetical order, each with a short definition. Use it as a reference while you read papers, and use the search tool below to test yourself.

A cloud of colored labels showing twenty-four research methods terms such as variable, hypothesis, reliability, validity, p-value, effect size, power and preregistration.
Twenty-four of the terms you now know. The full glossary is below.

What you will learn

  • The precise meaning of the core terms used throughout the course.
  • Which terms are easily confused and how to tell them apart.
  • How to look a term up quickly and test yourself.

Key terms

Easily confused pairs: reliability vs validity; anonymous vs confidential; independent vs dependent variable; p-value vs effect size; main effect vs interaction; correlation vs causation; replication vs reproducibility (re-running the same analysis on the same data).

The glossary

Term Meaning
Alpha The Type I error rate you accept, conventionally .05.
Alternative hypothesis The claim that an effect or difference exists.
Between-subjects design Each participant is in only one condition.
Blinding Hiding condition membership from participants (single) or participants and researchers (double).
Confidence interval A range of plausible values for a population quantity.
Confound A second variable that differs between conditions with the IV and offers a rival explanation.
Construct validity How well a measure or manipulation represents the concept intended.
Control group The comparison group that does not receive the key manipulation.
Correlation A statistical relationship between two variables; says nothing alone about cause.
Counterbalancing Varying condition order across participants to balance order effects.
Debriefing Explaining the true purpose and any deception after a study.
Demand characteristics Cues that suggest to participants how they should behave.
Dependent variable (DV) The outcome that is measured.
Effect size The magnitude of an effect, such as d or r, independent of sample size.
External validity The extent to which findings generalize to other people, settings and times.
Factorial design A design with two or more independent variables in all combinations.
HARKing Hypothesizing after the results are known.
Hypothesis A testable prediction derived from theory.
Independent variable (IV) The variable the researcher manipulates.
Informed consent Voluntary agreement to participate after being told what is involved.
Institutional review board (IRB) An independent committee that reviews studies with human participants.
Interaction The effect of one factor depends on the level of another.
Internal validity The extent to which a study supports a causal conclusion about the IV and DV.
Mean The arithmetic average.
Null hypothesis The claim of no effect that a test tries to reject.
Operational definition A concrete description of how a variable is measured or manipulated.
p-hacking Analyzing flexibly until p < .05 and reporting only that analysis.
p-value Probability of data at least as extreme as observed, if the null is true.
Population The entire group a researcher wants to draw conclusions about.
Power The probability of detecting a true effect of a given size.
Preregistration A time-stamped public plan made before data collection.
Random assignment Using chance to decide which condition each participant experiences.
Reliability Consistency of a measure across time, items or raters.
Replication Repeating a study to see whether the finding appears again.
Sample The subset of the population actually studied.
Standard deviation A measure of the typical spread of scores around the mean.
Standard error The standard deviation of a statistic's sampling distribution.
Type I error Rejecting a true null hypothesis (false positive).
Type II error Failing to reject a false null hypothesis (miss).
Within-subjects design Each participant experiences every condition.

Try it

A small searchable glossary. Edit the search term and run it. The same pattern, a dictionary and a filter, is how many study aids work.

JS Search the glossary

Press Run (or Ctrl + Enter) to see the console output here.

No output.

Check your understanding

Quick check ยท 4 questions

of 4 answered You scored / 4 ยท perfect!

  1. 1. Which pair describes consistency and accuracy of measurement respectively?

    Reliability is consistency; validity is whether the measure captures the intended concept.
  2. 2. A range of plausible values for a population quantity is a...

    Confidence intervals show both the estimate and its precision.
  3. 3. Which term means hiding the group a participant is in?

    Blinding prevents expectations about condition from shaping behavior or scoring.
  4. 4. 'Reproducibility' differs from 'replication' because it means...

    Reproducibility checks the analysis; replication collects new data.

Summary

  • Many pairs of terms sound alike but mean different things; the glossary distinguishes them.
  • Design terms (IV, DV, confound, control) and statistics terms (alpha, p, power, effect size) work together.
  • Ethics and open-science terms (consent, IRB, preregistration, replication) describe the promises researchers make.

Next: Research methods cheat sheet