A topic in the Open Knowledge Graph — a free, open map of 15,290 topics and the order to learn them in.
Descriptive research methods document what people think, feel, or do without manipulating variables. The three main types are naturalistic observation, surveys, and case studies. These methods answer 'what' and 'how often' questions and are ideal for early-stage inquiry into a phenomenon. Descriptive methods cannot establish causation, but they generate hypotheses and provide a rich picture of psychological phenomena in real-world contexts.
For a given psychological question, decide which descriptive method is most appropriate and justify the choice based on the goals, ethical constraints, and practical considerations of each approach.
When you finish studying the scientific method, the next question is: what are the actual tools researchers use to gather data before running an experiment? Descriptive research methods — naturalistic observation, surveys, and case studies — are that toolkit. They are not a step down from experimentation; they serve a different purpose. Descriptive methods answer "what" questions: what do people do in real settings? What do large populations believe? What happened in one individual's unusual experience? These questions must be answered before you can design an experiment to test why.
Naturalistic observation involves watching behavior in its real context without intervening. A developmental psychologist might observe how children interact on a playground; a clinical researcher might document behavior patterns in a psychiatric ward. The strength is ecological validity — behavior is real, not lab-induced. The risk is the Hawthorne effect: when people know they are being observed, they often behave differently. Covert observation reduces this risk but raises ethical questions about informed consent.
Surveys allow you to reach large samples quickly and measure attitudes, beliefs, and behaviors that would never appear in direct observation. The major threats to validity are social desirability bias (people answer as they think they should, not as they actually feel) and question wording effects (how a question is phrased shapes the answer). Surveys describe what people say — not always what they do.
Case studies go deep on a single individual, group, or event. They are invaluable when the phenomenon is rare, when you need longitudinal detail, or when context matters so much that averaging across many cases would destroy the signal. The tradeoff is low generalizability — one case tells you a great deal about that case and may suggest hypotheses, but cannot confirm that findings apply broadly.
The unifying limitation across all three methods is that description is not explanation. Seeing that two variables co-occur, or that one type of person behaves differently from another, does not reveal which caused which — or whether a third variable caused both. That is the domain of experimental research. Think of descriptive methods as building the map; experiments test the routes.