Source: The Measure of Mind, pp. 42–45 (2-2a), pp. 64–66 (2-5)
Tags: descriptive methods, naturalistic observation, case study, survey, correlational research, ethics in psychology, IRB, informed consent, APA guidelines, Milgram, Tuskegee, research design, Psychology 1100, Ohio State
Difficulty: Foundational Prerequisites: None. This is one of the first units in the course and underpins everything else.
This material covers two foundational pieces of the research methods unit: the types of descriptive research psychologists use (and their limitations), and the ethical rules that govern how research with human participants is conducted. You need both to make sense of every study referenced later in the course. If you cannot identify the difference between a case study and a naturalistic observation, or explain why informed consent exists, the rest of the material will feel like a list of disconnected facts. These topics were among the most missed on Midterms 1 and 2, and the final will test them again.
Descriptive methods (naturalistic observation, surveys, case studies) let psychologists describe behaviour without manipulating variables, but none of them can establish cause and effect. Ethical research requires informed consent, minimisation of harm, confidentiality, and oversight by an Institutional Review Board (IRB), all of which trace back to historical abuses that made regulation necessary.
Descriptive methods
Research strategies designed to observe and record behaviour as it occurs, without manipulating any variable. Think of these as the "what is happening?" tools, not the "why is it happening?" tools.
Naturalistic observation
Watching and recording behaviour in its natural setting, without intervening. In simple terms, this means you sit, watch, and take notes, the way Jane Goodall observed chimpanzees in the wild.
Case study
An in-depth investigation of a single individual, group, or event. Think of it as a deep dive into one story rather than a broad sweep across many.
Survey
A method of collecting self-reported data from a large group, typically through questionnaires or interviews. In simple terms, you ask a lot of people the same set of questions and look for patterns.
Correlation
A statistical measure of the relationship between two variables, ranging from -1.0 to +1.0. A positive correlation means both variables move in the same direction; a negative correlation means they move in opposite directions.
Correlation does not imply causation
The principle that observing a relationship between two variables does not prove that one causes the other. There may be a third variable, or the direction of influence may be reversed. This is the single most repeated warning in introductory psychology.
Institutional Review Board (IRB)
A committee that reviews research proposals to ensure they meet ethical standards before any data collection begins. Think of it as the ethics gatekeeper for every study that involves human participants.
Informed consent
A participant's voluntary agreement to take part in a study after being told what the study involves, including any risks. In simple terms, you cannot experiment on people without telling them what they are signing up for.
Debriefing
The process of explaining the true purpose of a study to participants after it ends, especially when any deception was used. This is the researcher's obligation to "come clean."
Confidentiality
The ethical principle that a participant's personal data will not be made publicly identifiable. This is distinct from anonymity (where not even the researcher knows who provided which data).
Descriptive methods share one defining feature: they observe and record without manipulating an independent variable.
Because there is no manipulation, descriptive methods cannot establish causation. They can describe patterns, suggest relationships, and generate hypotheses, but the "why" question requires an experiment.
The researcher watches behaviour in the environment where it would occur anyway: a playground, a classroom, a hospital ward.
Strength: high ecological validity. Behaviour is genuine because participants are in their normal context.
Weakness: observer bias (the researcher sees what they expect to see) and lack of control over extraneous variables.
Participant reactivity is a concern. If people know they are being watched, their behaviour may change. This is sometimes called the Hawthorne effect, though that term is debated.
Used when a phenomenon is rare or when depth matters more than breadth. Classic examples include Phineas Gage (brain injury and personality change) and H.M. (memory and the hippocampus).
Strength: rich, detailed data that a survey could never capture.
Weakness: findings from a single case may not generalise to the wider population. One unusual patient does not prove a rule.
Surveys can reach thousands of people quickly and cheaply.
Strength: efficient for measuring attitudes, beliefs, and self-reported behaviour across large samples.
Weaknesses:
Wording effects: small changes in how a question is phrased can shift responses significantly.
Social desirability bias: people tend to answer in ways that make them look good.
Sampling bias: if the sample is not representative, the results do not generalise.
A correlation coefficient (r) quantifies the strength and direction of a relationship.
r = +1.0: perfect positive correlation
r = -1.0: perfect negative correlation
r = 0: no linear relationship
The absolute value of r tells you the strength. An r of -0.80 is a stronger relationship than an r of +0.30.
The third-variable problem: an observed correlation between A and B may be driven by an unmeasured variable C. Ice cream sales and drowning rates both rise in summer, but heat (the third variable) drives both.
Modern research ethics grew out of documented abuses:
The Tuskegee syphilis study (1932–1972): African American men with syphilis were left untreated, without their knowledge, so researchers could observe the disease's progression.
Milgram's obedience experiments (1961): participants were led to believe they were delivering painful electric shocks to another person. The study produced valuable findings but caused significant psychological distress.
These cases (and others) led directly to the ethical codes now in place.
The Belmont Report (1979) established three core principles for research with human participants:
Respect for persons: individuals must be treated as autonomous agents, and those with diminished autonomy deserve extra protection.
Beneficence: researchers must minimise harm and maximise benefit.
Justice: the burdens and benefits of research must be distributed fairly. You cannot recruit only vulnerable populations to bear the risks while others reap the benefits.
Informed consent: participants must know what they are agreeing to. For children or other vulnerable groups, a legal guardian provides consent and the participant provides assent.
Right to withdraw: a participant can leave a study at any time without penalty.
Debriefing: required after any study involving deception. The researcher explains the true purpose and ensures no lasting harm.
Confidentiality: data must be stored and reported in ways that protect participants' identities.
IRB approval: required before data collection begins. The board weighs risks against potential benefits and can reject or require modifications to a study.
Deception: permitted only when the study cannot be done otherwise, when the potential findings justify it, and when participants are debriefed afterward. Deception about risks that would affect willingness to participate is not permitted.
Animal research follows a separate but related framework. The three Rs apply:
Replacement: use non-animal alternatives when possible.
Reduction: use the minimum number of animals necessary.
Refinement: minimise pain and distress.
An Institutional Animal Care and Use Committee (IACUC) reviews proposals involving animal subjects.
Descriptive methods are the backbone of epidemiology (tracking disease outbreaks), market research (consumer surveys), and clinical case formulation. Ethical oversight, meanwhile, is why you sign a consent form before a medical procedure or a psychology experiment. The safeguards exist because real people were harmed in their absence.
"Correlation means there is no relationship." A correlation of zero means no linear relationship, but a strong correlation absolutely means the variables are related. The mistake is confusing "correlation does not imply causation" with "correlation means nothing."
"Naturalistic observation is the same as a case study." Naturalistic observation watches behaviour broadly in a natural setting; a case study is a deep dive into one specific individual or event. They overlap sometimes but are different methods.
"If a study is ethical today, it was always ethical." The Milgram and Tuskegee studies were legal at the time. Ethical standards evolve, and what was once accepted may now be considered unacceptable.
"Informed consent means the participant knows everything about the study." In studies using deception, informed consent covers risks and general procedures but may withhold the specific hypothesis. Full disclosure comes during debriefing.
⚠️ You will be asked to identify which descriptive method is being used in a scenario. Be able to distinguish naturalistic observation, case study, and survey from each other and from experiments.
⚠️ Expect a question testing whether you understand that correlation does not equal causation, likely with a scenario requiring you to spot the third-variable problem.
⚠️ Know the specific ethical safeguards (informed consent, debriefing, IRB) and be able to apply them to a described scenario, not just define them.
⚠️ Historical studies (Tuskegee, Milgram) are fair game. Know what made them ethically problematic and which principles they violated.
True or False: A correlation of -0.85 indicates a weaker relationship than a correlation of +0.50.
A: False. The absolute value determines strength. -0.85 is stronger than +0.50.
Fill in the blank: The committee that must approve a research study before data collection begins is called the ________.
A: Institutional Review Board (IRB).
True or False: Naturalistic observation allows researchers to establish cause-and-effect relationships.
A: False. Without manipulation of variables, no descriptive method can establish causation.
Fill in the blank: The ethical principle requiring researchers to explain a study's true purpose after deception is called ________.
A: Debriefing.
Q: A researcher observes children's playground behaviour through a one-way mirror without interacting with them. What descriptive method is this?
A: Naturalistic observation. The researcher is recording behaviour in a natural setting without intervention.
Q: A study finds a strong positive correlation between hours of sleep and exam scores. Can we conclude that sleeping more causes better grades? Why or why not?
A: No. Correlation does not establish causation. A third variable (such as better time management or lower stress) could explain both more sleep and higher scores.
Q: What three core principles did the Belmont Report establish?
A: Respect for persons, beneficence, and justice.
Q: A researcher wants to study how people respond to being publicly embarrassed but does not tell participants this is the true purpose. What ethical safeguard must the researcher provide after the study?
A: Debriefing. The researcher must explain the study's true purpose and ensure the participant has not been harmed.
Q: Why is the Tuskegee syphilis study considered a landmark case in research ethics?
A: Participants (African American men) were not informed they had syphilis and were denied treatment so researchers could observe the disease's natural course. The study violated informed consent, beneficence, and justice, and it continued for 40 years.
This material connects directly to every empirical study discussed in the course. When you encounter a finding later (sleep and memory, conditioning, intelligence testing), you should be able to ask: "What method produced this finding, and could the design support a causal conclusion?" The ethical principles here also reappear in the clinical and social psychology units, where issues of consent and harm are central to practice.
Related Terms / Search Tags: descriptive research methods, naturalistic observation psychology, case study method, survey research bias, correlation vs causation, third variable problem, IRB institutional review board, informed consent psychology, debriefing after deception, Belmont Report principles, APA ethics code, Tuskegee syphilis study, Milgram obedience experiment, research ethics psychology, PSYCH 1100 final exam, Ohio State psychology