Experiments: variables, hypotheses and control

The three variables

The independent variable (IV) is what the researcher changes. The dependent variable (DV) is what is measured. Controlled variables are everything held constant so that any change in the DV can be attributed to the IV. Every experimental question in Paper 2 begins by asking you to name these.

Operationalisation

A variable must be defined so precisely that another researcher could measure it the same way. “Aggression” is not operationalised; “number of physical contacts with the doll in a $20$-minute observation” is. Marks are lost far more often for vague operationalisation than for wrong theory.

Hypotheses

A directional (one-tailed) hypothesis predicts which way the difference will go; a non-directional (two-tailed) one predicts a difference without saying which way. Use directional only when previous research supports the direction. The null hypothesis states there is no difference beyond chance — and it must always be written as a testable sentence, not as “nothing will happen”.

Extraneous and confounding variables

An extraneous variable could affect the DV; a confounding variable actually does, and varies systematically with the IV. Noise affecting both groups equally is extraneous; noise affecting only one group is confounding — and confounding is the one that destroys the study.