Research Methodology in Social Sciences

These flashcards encompass key terms and concepts related to research methodology in social sciences, aiding in understanding and review for examinations.

Positivism

An approach that seeks causal, law-like, observable regularities; emphasizes testable hypotheses and falsification.

Interpretivism

An approach centered on meaning-making, context, and symbols; emphasizes thick description over universal laws.

Quantitative methods

Use numerical data and statistical analysis to test hypotheses and identify patterns across large-N samples.

Qualitative methods

Use non-numerical, case-based evidence (interviews, archives, ethnography) to explore meaning and mechanisms.

Independent Variable (IV)

The presumed cause; the variable manipulated or whose variation is expected to produce change in the dependent variable.

Dependent Variable (DV)

The outcome or effect to be explained.

Hypothesis / Falsifiability

A specific, testable claim about how X affects Y that could be proven wrong by evidence.

Deterministic vs. Probabilistic

Deterministic: X always produces Y; Probabilistic: X increases the likelihood of Y.

Modus tollens

If P → Q; not-Q; therefore not-P; a valid form in logic.

Fallacy of affirming the consequent

If P → Q; Q; therefore P; invalid reasoning that confuses correlation with causation.

Requirements of causality

The relationship must show covariation, time order, and non-spuriousness.

Empirical observation

Evidence that can be observed or measured; the basis for testing causal claims.

Theory

A logically consistent set of statements that explains observed regularities and produces testable predictions.

Concept

A general idea representing a class of phenomena used to build theories.

Operationalization

The process of turning an abstract concept into a measurable indicator or variable.

Law-like regularity

A recurring empirical pattern that suggests a causal process or general rule in social behavior.

Spurious relationship

When two variables move together because of a third factor, not because they directly affect each other.

Confounder / Lurking variable

A variable that is related to both X and Y, creating or masking an apparent relationship between them.

Antecedent variable

A prior cause that produces both the independent and dependent variables.

Intervening (mediator) variable

A mechanism or process through which X affects Y.

Causal mechanism

The specific process or pathway through which X influences Y.

Unit of analysis

The entity being studied or measured, such as individuals, groups, or organisations.

Ecological fallacy

Mistakenly inferring individual-level behavior from aggregate data.

Individualistic fallacy

Ignoring group-level or structural factors when explaining individual outcomes.

QALMRI framework

A structure for summarizing research: Question, Alternatives, Logic, Methods, Results, Inferences.

Research hypothesis

A specific, testable statement predicting a relationship between variables.

Null hypothesis

The default assumption that there is no relationship or effect.

Critical case / Crucial test

A case that can strongly confirm or disconfirm a theory.

Inductive reasoning

Moving from specific observations to general theories.

Deductive reasoning

Starting with theory or principles and deriving testable hypotheses.

Correlation vs. causation

Correlation shows association; causation requires covariation, time order, and non-spuriousness.

Covariation

A change in one variable is associated with a change in another.

Time order

The cause (independent variable) must occur before the effect (dependent variable).

Non-spuriousness

The observed relationship is not due to another variable influencing both X and Y.

Causal inference

Drawing a conclusion that a relationship between variables is causal rather than coincidental.

Alternative explanations

Rival hypotheses that could explain the observed outcome besides the proposed cause.

Necessary cause

A factor that must be present for the outcome to occur.

Sufficient cause

A factor that, if present, guarantees the outcome.

Conceptual definition

The abstract meaning of a concept stated in words without specifying how to measure it.

Operational definition

The specific procedures or indicators used to measure a concept in the real world.

Indicator

A concrete measure or question used to capture variation in a concept.

Variable

A characteristic that varies across cases or units of analysis and can be measured or categorized.

Tautology

A statement that is true by definition and therefore untestable.

Multidimensional concept

A concept that contains multiple aspects or components that must be measured separately.

Validity

The degree to which a measure accurately reflects the concept it is intended to represent.

Reliability

The degree to which a measure yields consistent results across time, coders, or items.

Measurement

The process of systematically assigning numbers or labels to units of analysis to represent conceptual properties.

Measurement error

The difference between the true value and the measured value.

Systematic error (bias)

Consistent over- or under-estimation of the true value.

Random error (noise)

Unpredictable variation that makes a measure inconsistent.

Nominal level of measurement

Categories without any inherent order.

Ordinal level of measurement

Ordered categories with unequal intervals.

Interval level of measurement

Ordered, equal intervals with no true zero.

Ratio level of measurement

Ordered, equal intervals with a true zero point.

Categorical variables

Nominal or ordinal variables with distinct groups or categories.

Quantitative variables

Interval or ratio variables that take numerical values.

Discrete variable

Takes on whole-number values only.

Continuous variable

Can take on fractional values.

Face validity

Whether a measure appears on its face to capture the intended concept.

Content validity

Whether a measure covers the full range of meanings or dimensions of the concept.

Construct validity

Whether a measure correlates appropriately with other measures of the same or opposite concepts.

Predictive validity (criterion validity)

Whether a measure predicts outcomes it should theoretically predict.

Internal consistency

The degree to which multiple items measuring the same concept are correlated.

Test-retest reliability

Whether a measure gives similar results at two points in time.

Inter-rater reliability

The degree of agreement among different coders or raters.

Index

A composite measure created by combining multiple indicators into a single score.

Scale

A measure that assigns scores to responses to capture intensity or degree of a concept.

Likert scale

A common ordinal scale where respondents indicate agreement or disagreement.

Survey question wording

The phrasing of survey items which can affect validity.

Social desirability bias

The tendency of respondents to give socially acceptable answers rather than true ones.

Reliability–validity relationship

A measure must be reliable to be valid.

Example of measurement in practice

Jencks on poverty measurement showing conceptual vs. operational definitions.

Experiment diagram (true experiment)

Diagrammatic representation showing experimental and control groups for true experimental designs.