Source: Exam 1 Study Guide | General Psychology, The Ohio State University
Difficulty: Introductory | Prerequisites: None. This is typically the first unit in the course.
Research methods is the foundation for everything else in this course. Before you study the brain, perception, or consciousness, you need to understand how psychologists gather and evaluate evidence. This unit teaches you to tell good studies from weak ones, to spot when someone is drawing causal claims from correlational data, and to think critically about the research you will read for the rest of the term. If you are coming in cold, start here: every later unit assumes you know what an independent variable is and why random assignment matters.
Psychologists use the scientific method to study behaviour: form a hypothesis, operationalise your variables, collect data, analyse it. The three main study designs are descriptive, correlational, and experimental, and only experiments can establish cause and effect. You also need to know basic statistics (mean, median, mode), how to evaluate a study's reliability and validity, and what makes research ethical.
Confirmation bias
The tendency to search for, interpret, and remember information that confirms what you already believe, while ignoring evidence that contradicts it. In simple terms, you see what you expect to see.
Critical thinking
Evaluating claims by examining evidence, questioning assumptions, and considering alternative explanations before accepting a conclusion. Think of it as the opposite of taking things at face value.
Variable
Any factor that can change or be changed in a study. It is what researchers measure or manipulate. In simple terms, it is anything in an experiment that is not fixed.
Operationalisation
Defining an abstract concept in measurable, concrete terms so it can be studied. For example, defining "aggression" as the number of times a child hits a toy. Think of it as translating a vague idea into something you can actually count or observe.
Independent variable (IV)
The variable the researcher deliberately manipulates or changes to see its effect. In simple terms, the thing you tweak on purpose.
Dependent variable (DV)
The variable that is measured to see whether the IV had an effect. Think of it as the outcome, the result you are watching for.
Experimental group
The group that receives the treatment or manipulation (the IV).
Control group
The group that does not receive the treatment. It serves as a baseline for comparison.
Random assignment
Every participant has an equal chance of being placed in any condition. This is what allows researchers to draw causal conclusions, because it distributes potential confounds evenly across groups.
Confounding variable
An unmeasured variable that varies with the IV and could explain the results instead. If present, you cannot be sure whether the IV or the confound caused the change in the DV.
Third variable
In a correlational study, an outside variable that may be driving the relationship between the two measured variables. Classic example: ice cream sales and drowning rates both rise in summer, but the third variable is warm weather.
Correlation
A statistical measure of the relationship between two variables. Positive correlation: both variables move in the same direction. Negative correlation: one goes up while the other goes down. Correlation does not imply causation.
Descriptive study
Research that describes or documents behaviour (e.g. surveys, case studies, naturalistic observation) without manipulating variables.
Correlational study
Research that measures the relationship between two or more variables without manipulating any of them. Cannot establish cause and effect.
Experimental study
Research that manipulates an IV and measures a DV, using random assignment and a control group. The only design that can establish causation.
Cross-sectional study
Compares different groups of people at one point in time (e.g. comparing 20-year-olds and 60-year-olds today).
Longitudinal study
Follows the same group of people over an extended period to observe change over time.
Mean
The arithmetic average of a set of scores. Add them up and divide by the number of scores. Sensitive to outliers.
Median
The middle value when scores are arranged in order. Less affected by extreme scores than the mean.
Mode
The most frequently occurring score in a data set.
Reliability
The consistency of a measure. A reliable test gives similar results each time it is used under the same conditions. Think of it as: does the ruler give you the same reading twice?
Validity
Whether a measure actually measures what it claims to measure. Think of it as: is the ruler measuring height, or something else entirely?
Psychologists follow the same basic research cycle: observe, form a hypothesis, design a study, collect data, analyse, draw conclusions, report.
A good hypothesis is testable and falsifiable. If there is no possible outcome that would prove it wrong, it is not scientific.
Operationalisation is what bridges the gap between an abstract idea ("stress") and something you can measure (cortisol levels in saliva, self-report scores on a 1 to 10 scale).
Descriptive research describes what is happening, without explaining why. Includes surveys, case studies, and naturalistic observation.
Strength: captures real-world behaviour.
Limitation: cannot explain causes.
Correlational research measures the statistical relationship between two variables.
A positive correlation means both variables increase together (e.g. study hours and exam scores).
A negative correlation means one increases while the other decreases (e.g. hours of sleep lost and cognitive performance).
Strength: identifies patterns and allows prediction.
Limitation: cannot establish cause and effect. The third variable problem is always lurking.
Experimental research manipulates an IV and measures its effect on a DV, while controlling other factors.
Uses random assignment to distribute individual differences across groups.
Includes at least one experimental group and one control group.
Strength: the only design that can establish causation.
Limitation: can be artificial (low ecological validity), and some questions cannot ethically be tested with experiments.
Correlation coefficients range from -1.0 to +1.0.
The sign tells you the direction (positive or negative). The absolute value tells you the strength.
A correlation of 0 means no linear relationship.
Always ask: could a third variable explain this? If the answer is yes, you cannot claim causation.
The IV is what you manipulate. The DV is what you measure.
Random assignment is what makes an experiment an experiment. Without it, you have a quasi-experiment at best.
A confounding variable is any uncontrolled factor that co-varies with the IV. It threatens internal validity because you can no longer be sure the IV alone caused the change in the DV.
Cross-sectional: snapshot at one moment. Quick and cheap, but differences between age groups might reflect generational differences (cohort effects) rather than actual developmental change.
Longitudinal: tracks the same people over time. More expensive and time-consuming, but captures real change. Vulnerable to attrition (people dropping out).
Mean: add all scores, divide by the number of scores. Pulled by outliers.
Median: the middle score. Better than the mean when the distribution is skewed.
Mode: the most common score. The only measure that works for categorical data.
A measure can be reliable without being valid (a broken scale that always reads 5 kg is reliable but not valid).
A measure cannot be valid without being reliable. If it gives different results every time, it is not measuring anything consistently.
High reliability + high validity is the goal.
Informed consent: participants must know what they are getting into.
Right to withdraw: participants can leave a study at any time without penalty.
Confidentiality: data must be kept private.
Debriefing: after the study, researchers explain the true purpose, especially if deception was used.
Institutional Review Boards (IRBs) review research proposals to protect participants.
The principle of minimal risk: the study should not expose participants to harm beyond what they encounter in daily life.
Students often think a strong correlation means one variable causes the other. It does not. Correlation only tells you two things move together; a third variable could be responsible.
Students confuse random assignment with random sampling. Random sampling is how you recruit participants from a population (for generalisability). Random assignment is how you sort participants into groups within an experiment (for causation).
Students sometimes think the control group "does nothing." The control group does everything the experimental group does, minus the treatment. That is what makes the comparison fair.
Students often treat reliability and validity as the same thing. A test can be perfectly reliable (consistent every time) yet completely invalid (measuring the wrong thing).
⚠️ Know the difference between the three study designs and what each one can and cannot conclude.
⚠️ Be able to identify the IV, DV, experimental group, control group, and any confounding variables in a scenario.
⚠️ "Correlation does not imply causation" will come up. Be ready to explain why, using the third variable problem.
⚠️ Understand when to use mean vs. median vs. mode, especially with skewed distributions.
⚠️ Be able to distinguish reliability from validity and give examples of each.
⚠️ Know the core ethical principles (informed consent, debriefing, right to withdraw, confidentiality).
True or False: A correlational study can establish that one variable causes changes in another.
The variable a researcher manipulates is called the __________ variable.
True or False: A test that gives the same result every time is always valid.
The measure of central tendency most affected by extreme scores is the __________.
True or False: Random assignment ensures that each participant has an equal chance of being in any condition.
Q: A researcher finds that students who sleep more tend to earn higher grades. Can the researcher conclude that sleep causes better grades? Why or why not?
A: No. This is a correlational finding, so causation cannot be established. A third variable (e.g. better time management) could explain both more sleep and higher grades.
Q: In an experiment testing whether caffeine improves reaction time, what is the independent variable and what is the dependent variable?
A: The IV is caffeine (whether or not participants receive it, or how much). The DV is reaction time.
Q: A researcher gives the same personality test to a group of participants on two occasions, two weeks apart, and gets very different results each time. What does this suggest about the test?
A: The test has low reliability. A reliable test should produce consistent results under similar conditions.
Q: Why is random assignment important in experiments?
A: Random assignment distributes individual differences (personality, motivation, prior knowledge) evenly across conditions, so any difference in the DV can be attributed to the IV rather than to pre-existing differences between groups.
Q: A study compares the memory performance of 20-year-olds and 70-year-olds tested on the same day. What type of design is this, and what is its main limitation?
A: This is a cross-sectional design. Its main limitation is cohort effects: any difference might reflect generational differences (e.g. education quality, technology exposure) rather than ageing itself.
This connects to Unit 2 (Neuroscience) because the brain-imaging studies you will read there are all experiments or correlational designs, and you need to evaluate them with the tools from this unit. It also connects to Unit 3 (Sensation and Perception) where psychophysics research relies on operationalised thresholds and controlled experiments. Essentially, every study cited in this course was designed using the methods covered here.
Research methods, scientific method, psychology research design, confirmation bias, operationalisation, operationalization, IV DV, independent variable dependent variable, correlational study, experimental design, random assignment, confounding variable, third variable problem, cross-sectional study, longitudinal study, mean median mode, central tendency, reliability validity, ethics in psychology, informed consent, debriefing, IRB, PSYCH 1100, general psychology, Ohio State