Research Designs (Ch. 5)

Experiments

Studies where researchers manipulate variables to test cause-effect relationships.

Causation

When one variable directly affects another.

Joint method of agreement and difference

A logic method to determine causation by comparing cases where an effect occurs and doesn't occur.

Ceiling effect

When scores are too high, limiting differences between groups.

Floor effect

When scores are too low, limiting differences between groups.

Control variable

A factor kept constant to prevent it from affecting results.

Confound

A variable that unintentionally influences the outcome, making it hard to determine true causation.

Third-variable problem

A hidden factor that affects both studied variables, creating a false correlation.

Directionality problem

Uncertainty about which variable causes the other in a correlation.

Independent variable

The factor manipulated by the researcher.

Dependent variable

The factor measured in response to changes in the independent variable.

Internal validity

The degree to which a study accurately establishes a cause-effect relationship.

Testing intact groups

Using pre-existing groups, which can introduce bias.

Maturation and history

Natural changes in participants over time that affect study outcomes.

Regression to the mean

Extreme scores tend to move closer to the average upon retesting.

External validity

The extent to which study results apply to real-world settings.

Demonstrations

Studies that show an effect without necessarily proving causation.

Correlational research

Studies that examine relationships between variables without manipulation.

Simpson's paradox

When trends appear in different groups but disappear or reverse when combined.