Chapter 2: Research Methods in Psychology

Comprehensive vocabulary flashcards covering research methodology, experimental and non-experimental designs, measurement validity, statistics, and ethical research principles.

Scientific method

The practice of basing beliefs on systematic, direct observations of the world by following the theory-data cycle.

Theory

A set of propositions about what people do and why.

Hypothesis

A specific prediction about what will happen in a study based on a theory.

Data

Observations collected from people at certain times or in certain situations during a study, usually recorded in numerical form.

Replication

Conducting a study more than once on a new sample of participants to verify if similar findings are obtained.

Body of research

A large set of published studies that all investigate the same research question.

Variable

Something of interest that varies from person to person or from situation to situation.

Measured variable

A variable that is observed and recorded in numeric form without experimental manipulation.

Manipulated variable

A variable whose values the researcher actively controls by assigning different participants to different levels.

Operational definition

The specific method used to measure or manipulate an abstract variable, turning it into a concrete number for statistical analysis.

Descriptive research

A type of research that focuses on one measured variable at a time with the primary goal of describing what is typical.

Random sampling

A method of selecting participants in which every member of the population of interest has an equal chance of being chosen without bias.

Biased sampling

A sampling error that occurs when only the most visible, motivated, opinionated, or easy-to-reach individuals are included in a sample.

Naturalistic observation

An observational research method that involves observing and recording behavior in everyday, real-world environments without interfering.

Case study

An in-depth investigation of one or two individuals, typically used to study unique conditions or rare phenomena.

Correlational research

A research design that measures two or more variables without manipulation to identify patterns of association between them.

Positive correlation

An association in which high scores on one variable correspond with high scores on another variable, producing a scatterplot that slopes upward from left to right.

Negative correlation

An association in which high scores on one variable correspond with low scores on another variable, producing a scatterplot that slopes downward from left to right.

Zero correlation

The complete absence of a systematic linear relationship between two measured variables.

Temporal precedence

A criterion for causation requiring that the proposed causal variable ($A$) clearly occurs earlier in time than the outcome variable ($B$).

Third-variable problem

An alternative explanation in correlational research where an unmeasured third variable ($C$) is responsible for the observed relationship between two variables.

Experimental research

A study design in which at least one variable is manipulated and another is measured to establish a cause-and-effect relationship.

Independent variable (IV)

The variable manipulated by the researcher that represents the hypothesized causal factor and contains at least two distinct levels.

Dependent variable (DV)

The measured outcome variable in an experiment that represents the hypothesized effect of the independent variable.

Random assignment

A method using chance to assign participants to experimental groups, ensuring individual differences are distributed equally across conditions.

Experimental group

The condition or group in an experiment that receives the active treatment or manipulated causal factor.

Control group

The comparison condition in an experiment in which the proposed causal factor is absent.

Placebo condition

An experimental condition in which participants receive an inert treatment (such as a sugar pill) while expecting an active intervention.

Double-blind procedure

A research control where neither the participants nor the research staff in direct contact with them know which treatment condition each person received.

Construct validity

The degree to which the operationalizations, tests, or measures used in a study accurately capture the theoretical variables of interest.

Reliability

The consistency and repeatability of a measurement across repeated trials, time periods, or independent observers.

External validity

The extent to which research findings obtained from a specific sample can be generalized to the broader population of interest.

Internal validity

The ability of an experimental design to eliminate alternative explanations and confounds, ensuring that changes in the dependent variable were caused solely by the independent variable.

Confound

An uncontrolled factor that accidentally varies systematically along with the independent variable, undermining internal validity by providing an alternative explanation for results.

Descriptive statistics

Mathematical computations or graphical techniques used to organize, summarize, and describe characteristics of a collected set of scores.

Frequency distribution

A bar graph displaying the possible values of a variable along the x-axis and the number of participants obtaining each score on the y-axis.

Mean

The arithmetic average of a dataset, calculated by summing all individual scores and dividing by the total number of scores.

Median

The middlemost score in a dataset that has been arranged sequentially from lowest to highest value.

Mode

The single score or value that appears most frequently in a distribution of data.

Range

A basic measure of data variability calculated as the difference between the highest and lowest scores in a dataset.

Standard deviation

A statistical measure of variability that quantifies how much scores in a distribution vary around their mean.

Correlation coefficient ($r$)

A standardized statistical metric ranging from $-1.0$ to $+1.0$ that reflects the strength and direction of the linear relationship between two variables.

Experimental effect size ($d$)

A standardized statistical measure that indicates how far apart two group means are in standard deviation units.

Inferential statistics

A collection of probabilistic techniques used to determine whether observed sample findings represent a true effect or difference in the broader population.

Null hypothesis

The baseline statistical assumption that there is no true relationship, association, or difference between variables in the population.

Statistical significance

A conclusion reached when an obtained result is unlikely to have occurred if the null hypothesis were true, conventionally defined as $p < .05$.

Meta-analysis

A quantitative research technique that mathematically averages the effect sizes across multiple independent studies on the same topic.

HARKing

The questionable practice of 'Hypothesizing After the Results are Known,' where researchers formulate hypotheses only after seeing study results and present them as a priori predictions.

p-hacking

Questionable data analysis practices—such as running multiple tests, selectively removing outliers, or adding participants—to drive a $p$-value below $0.05$.

Open science

The practice of openly sharing study materials, raw data sets, analysis protocols, and published papers to ensure research can be verified and replicated.

Preregistration

A transparent research practice in which scientists publicly record their study design, hypotheses, and analytical plan before collecting any data.

Institutional Review Board (IRB)

A multidisciplinary panel of researchers, educators, and community members tasked with reviewing research proposals to ensure ethical guidelines are upheld.

Autonomy

An ethical principle asserting an individual's right to freely choose whether to participate in research without coercion, implemented via informed consent, special protections for vulnerable groups, and debriefing.

Beneficence

The ethical obligation of researchers to protect participants from physical and psychological harm by weighing research risks against potential societal benefits.

Justice

The ethical principle requiring that the burdens of research participation are distributed fairly and that the participants represent the population likely to benefit from the research.

OCAP® principles

A set of standards governing Indigenous research data representing Ownership, Control, Access, and Possession by First Nations communities.

Replacement

The ethical guideline directing researchers to seek alternatives to live animal subjects, such as computer simulations, whenever feasible.

Refinement

The ethical guideline requiring researchers to modify experimental procedures and animal care practices to minimize or eliminate pain and distress.

Reduction

The ethical guideline stating that researchers should design experiments to use the fewest animal subjects possible while still obtaining valid findings.

Animal welfare

The position that animals should be protected from unnecessary suffering and distress during scientific research.

Animal rights

The philosophical belief that animals possess inherent moral rights equal to humans and therefore should never be utilized in scientific experimentation.